maintain-formal-verification-skill
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources which could contain malicious instructions designed to hijack the agent's behavior.\n
- Ingestion points: SKILL.md (reads commit messages, code comments, changelogs, and an external host-adapter.md reference).\n
- Boundary markers: Absent; there are no instructions to the agent to treat external content as untrusted or to ignore embedded instructions.\n
- Capability inventory: SKILL.md (executes shell commands to run verification tools and writes updates to verification files and skills).\n
- Sanitization: Absent; the skill does not specify any validation or sanitization for the data retrieved from commits or code before processing it.\n- [COMMAND_EXECUTION]: The skill executes shell commands that are dynamically retrieved from other project-local skills or configuration files.\n
- Evidence: SKILL.md instructs the agent to find a verify skill and execute "the command that runs it" to perform checks.
Audit Metadata