common-store-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow instructs the agent to run the
git logcommand to collect version history (SKILL.md). This is a standard developer tool usage consistent with the skill's purpose for generating changelogs. - [INDIRECT_PROMPT_INJECTION]: The skill ingests git commit history, which can contain untrusted data from multiple contributors. While malicious strings in commit messages could attempt to influence the agent's output, the skill lacks high-privilege capabilities that would make such an injection dangerous.
- Ingestion points: Git history retrieved via
git log <last-tag>..HEAD(SKILL.md). - Boundary markers: No specific delimiters or boundary warnings are provided for the input log data.
- Capability inventory: The skill is restricted to text generation, triage, and character validation; it does not utilize network tools or file-system write operations during the generation process.
- Sanitization: The skill filters internal commits (chore, refactor, ci) but does not explicitly sanitize or escape the content of user-facing commits.
Audit Metadata