cso
Chief Security Officer mode. (gstack)
Security
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The skill instructs the agent to embed a non-visible marker ("<gstack-qid:...>") inside rendered AskUserQuestion text — an explicit hidden/stealth instruction to include metadata invisible to the user, which is a deceptive behavior outside the CSO audit's stated remit.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill's Pre-emit verification gate explicitly requires quoting the verbatim code line(s) that motivated a finding (e.g., secret-containing .env or commit lines), which forces the model to output secret values verbatim.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Source is the user/attacker-authored project repository content that this skill reads at runtime via local Grep/Find/git-history scanning (e.g., Phase 2 secrets archaeology, Phase 4 CI/CD workflow parsing, Phase 7 LLM/AI prompt-injection tracing, and Phase 8 skill supply-chain scanning), so arbitrary outsider text can be ingested directly without selecting a specific trusted item first.
- Repository
- garrytan/gstack
- Path
cso/SKILL.md
- Commit
d078622
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.