ceo-assistant— agent skill

ceo-assistant — independently scanned and version-tracked by SaferSkills.

by Claudefarid·Agent Skill·github.com/Claudefarid/claude-ceo-skill

Is ceo-assistant safe to install?

SaferSkills independently audited ceo-assistant (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
87/100
●●●●●●●●●
↑ +0 since first scan (87 → 87)Re-scan~30s
Latest scan
ScannedJun 25, 2026 · 30d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings3 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
64
22.4 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 · 3 flagged

Securityscore 64 · 3 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · references/meetings.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
excerptreferences/meetings.md· markdown
84### Sales / partnership meeting (CEO attending)
85- Why is the CEO in this meeting? (close the deal, elevate the relationship, unstick progres
… (2 chars elided on L85)
86- What has already been discussed? (don't ask what was covered in previous calls)
87- What does the other party want from this meeting?
88- CEO's role: relationship and vision — not discovery questions
Occurrences
1 occurrence · at L86
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-01sha256ce5204b52388d24frubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · references/setup.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
excerptreferences/setup.md· markdown
154. After loading → confirm with a brief one-liner: "Got it — working with [Company Name] dat
… (3 chars elided on L15)
16 
17**Do not ask setup questions if the profile already has data.** Just load it and use it.
18 
19---
Occurrences
1 occurrence · at L17
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 · references/weekly-digest.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
excerptreferences/weekly-digest.md· markdown
15- GA4 → sessions, conversions, top channels
16- Mixpanel → DAU/MAU, retention, activation
173. If tools are connected: generate digest from live data — do NOT ask the CEO to paste anyt
… (4 chars elided on L17)
184. If tools are NOT connected: say "I can pull this automatically if you connect HubSpot, GA
… (74 chars elided on L18)
195. Run the red flag check across ALL domains before writing
Occurrences
1 occurrence · at L17
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-01sha256010a4ca2189f0f8arubric 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.