reputation-management— agent skill

reputation-management — independently scanned and version-tracked by SaferSkills.

by indranilbanerjee·Agent Skill·github.com/indranilbanerjee/digital-marketing-pro

Is reputation-management safe to install?

SaferSkills independently audited reputation-management (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
83/100
●●●●●●●●○○
↑ +0 since first scan (83 → 83)Re-scan~30s
Latest scan
ScannedJun 23, 2026 · 35d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings4 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
52
18.2 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 · 4 flagged

Securityscore 52 · 4 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/reputation-management/SKILL.md
MEDIUMit 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
excerptskills/reputation-management/SKILL.md· markdown
379. **Check brand guidelines** — If `~/.claude-marketing/brands/{slug}/guidelines/_manifest.j
… (108 chars elided on L37)
38 
39Do not ask the user for information that already exists in their brand profile.
40 
41## Required Context
Occurrences
1 occurrence · at L39
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-01sha25668b030f55bcd484arubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/reputation-management/review-management-platforms.md
MEDIUMit 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
excerptskills/reputation-management/review-management-platforms.md· markdown
155- Never argue with a reviewer publicly
156- Never offer compensation publicly (do it privately)
157- Never ask a reviewer to change or remove their review
158- Always respond from a named person when possible (not "The Team")
159- Keep responses under 150 words for positive reviews, under 200 words for negative
Occurrences
1 occurrence · at L157
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-01sha2565084aa178cfd9d97rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · CONTRIBUTING.md
MEDIUMit 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
excerptCONTRIBUTING.md· markdown
1068. **If no brand exists**, say: "No brand profile found. Use /digital-marketing-pro:brand-se
… (21 chars elided on L106)
107 
108Do not ask the user for information that already exists in their brand profile.
109```
110 
Occurrences
1 occurrence · at L108
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-01sha25668b030f55bcd484arubric 365aacaView on GitHub
MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · skills/reputation-management/review-management-platforms.md
MEDIUMit 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
excerptskills/reputation-management/review-management-platforms.md· markdown
158- Always respond from a named person when possible (not "The Team")
159- Keep responses under 150 words for positive reviews, under 200 words for negative
160- Never reveal private customer details in a public response
161 
162---
Occurrences
1 occurrence · at L160
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-01sha256186bc3c0f8012890rubric 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.