changelog-generator
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from git commit histories to generate user-facing release notes.
- Ingestion points: The skill consumes external data in the form of git commit messages and history, as described in
SKILL.md(e.g., "Scans Git History") andaudit_output.json. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the content of commit messages as untrusted data or to ignore any instructions potentially embedded within them.
- Capability inventory: The agent is expected to read repository logs, categorize changes, and summarize technical descriptions into natural language.
- Sanitization: No sanitization, filtering, or validation steps are defined to handle malicious content within the commit messages before they are processed by the LLM.
Audit Metadata