Changelog Generator
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted data like git commit messages, feature lists, and code diffs to generate documentation. This represents a surface for indirect prompt injection attacks where malicious instructions hidden in the input data could attempt to manipulate the agent's output or actions.\n
- Ingestion points: The skill instructions in
SKILL.mdspecify processing 'git commits', 'feature lists', and 'code changes' provided by the user.\n - Boundary markers: There are no instructions or delimiters defined to help the AI distinguish between the skill's instructions and potentially malicious commands embedded within the input data.\n
- Capability inventory: The skill utilizes MCP tools
create_docxandmd_to_docxto generate files.\n - Sanitization: No input validation, filtering, or sanitization logic is present to handle adversarial content in the input text.
Audit Metadata