repo-doc-maintainer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading repository changes through
git diffandgit log. This creates a vulnerability where malicious instructions embedded in code comments or diffs could influence the agent's output when updating documentation. - Ingestion points:
git diff,git log, andgit statuscommands inSKILL.mdare used to read external repository content. - Boundary markers: The skill lacks explicit instructions to treat code comments or diff content as data rather than instructions.
- Capability inventory: The skill has the capability to write to local documentation files (
AGENTS.md,CLAUDE.md). - Sanitization: No sanitization or escaping of the ingested code content is performed before the agent processes it to decide on documentation updates.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local
gitcommands (git status,git diff,git log) to inspect the repository state. While these are standard development tools, they represent execution of shell commands based on the skill's workflow.
Audit Metadata