changelog-writing
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git commit logs and diffs to generate changelog summaries. This creates a surface for indirect prompt injection where malicious instructions embedded in commit messages could attempt to influence the agent's behavior. \n
- Ingestion points: Git history accessed via
git log <base-branch>..HEAD --onelineandgit diff <base-branch>..HEADas described in SKILL.md. \n - Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the input data. \n
- Capability inventory: Executes
git logandgit diffcommands to read repository state. \n - Sanitization: No explicit sanitization or filtering of commit message content is performed before summarization.\n- [COMMAND_EXECUTION]: Recommends the use of shell commands to audit project history.\n
- Evidence: Instructions include running
git logandgit diffto gather context for the changelog in SKILL.md.
Audit Metadata