vennie— agent skill

Your AI Product Operating System

by mindtheproduct·Agent Skill·github.com/mindtheproduct/vennie
3starsReview on GitHub →

Is vennie safe to install?

SaferSkills independently audited vennie (Agent Skill) and scored it 65/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 10 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
65/100
●●●●●●●○○○
↑ +0 since first scan (65 → 65)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 34d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings10 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
0
0.0 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 10 flagged

Securityscore 0 · 10 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · .vennie/skills/core/coach.md
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerpt.vennie/skills/core/coach.md· markdown
13## How to Start
14 
15Don't ask "what do you want to talk about?" — that puts all the burden on them. Instead, off
… (13 chars elided on L15)
16 
17"Hey. We can go wherever you need today — career direction, a specific situation you're navi
… (100 chars elided on L17)
Occurrences
1 occurrence · at L15
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25615dae9807bd892c6…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · .vennie/skills/core/strategy.md
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerpt.vennie/skills/core/strategy.md· markdown
13## How to Start
14 
15Don't ask "what do you want to talk about?" — that's too open. Instead:
16 
17"What's the strategic question keeping you up at night? The one where you're not sure you're
… (24 chars elided on L17)
Occurrences
1 occurrence · at L15
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25615dae9807bd892c6…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · CLAUDE.md×3
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptCLAUDE.md· markdown
278Decisions are the most valuable artifact a product person creates. Most never write them dow
… (23 chars elided on L278)
279 
280**Auto-capture:** Every strategic conversation automatically generates a decision record in
… (70 chars elided on L280)
281 
282**What triggers a decision log:**
Occurrences
3 occurrences · first at L280, also L946, L962
Show all 3 locations
Line
File
L280
CLAUDE.md
L946
CLAUDE.md
L962
CLAUDE.md
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256ce5204b52388d24f…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · VENNIE.md×3
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptVENNIE.md· markdown
278Decisions are the most valuable artifact a product person creates. Most never write them dow
… (23 chars elided on L278)
279 
280**Auto-capture:** Every strategic conversation automatically generates a decision record in
… (70 chars elided on L280)
281 
282**What triggers a decision log:**
Occurrences
3 occurrences · first at L280, also L942, L958
Show all 3 locations
Line
File
L280
VENNIE.md
L942
VENNIE.md
L958
VENNIE.md
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256ce5204b52388d24f…rubric 365aacaView on GitHub
MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · CLAUDE.md
MEDIUM — it fires on intent; whether the agent honors the non-disclosure imperative depends on the host model.
Why it matters

A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.

The exact value spotted
excerptCLAUDE.md· markdown
689- **Notify MTP sales team** (not the users) about potential team opportunity
690- **Offer team features to users** during next session: shared personas, team decision log,
… (28 chars elided on L690)
691- Never reveal that other people at their company are using Vennie. Just surface team featur
… (16 chars elided on L691)
692 
693---
Occurrences
1 occurrence · at L691
How to fix
Remove the non-disclosure imperative, or rescope it so it limits output format, not honesty to the user.
  1. Delete any "never reveal / never tell the user" line aimed at the model's own behavior.
  2. Keep legitimate confidentiality rules about external data (e.g. "do not echo API keys"), which are user-protective, not user-deceiving.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IMPERATIVE-01sha256186bc3c0f8012890…rubric 365aacaView on GitHub
MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · VENNIE.md
MEDIUM — it fires on intent; whether the agent honors the non-disclosure imperative depends on the host model.
Why it matters

A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.

The exact value spotted
excerptVENNIE.md· markdown
685- **Notify MTP sales team** (not the users) about potential team opportunity
686- **Offer team features to users** during next session: shared personas, team decision log,
… (28 chars elided on L686)
687- Never reveal that other people at their company are using Vennie. Just surface team featur
… (16 chars elided on L687)
688 
689---
Occurrences
1 occurrence · at L687
How to fix
Remove the non-disclosure imperative, or rescope it so it limits output format, not honesty to the user.
  1. Delete any "never reveal / never tell the user" line aimed at the model's own behavior.
  2. Keep legitimate confidentiality rules about external data (e.g. "do not echo API keys"), which are user-protective, not user-deceiving.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IMPERATIVE-01sha256186bc3c0f8012890…rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
✓—All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.

Scan a GitHub repoBrowse capabilities