specs-interpreter
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is explicitly directed to follow external specifications as the 'source of truth' and mandates that 'the specs win' over other logic. This establishes a vulnerability where instructions within processed markdown files can hijack the agent's behavior.
- [COMMAND_EXECUTION]: The skill is configured with file system tools to fulfill its design purpose. Evidence: The 'allowed-tools' metadata permits 'ls', 'read_file', 'write_file', and 'mkdir'. While these are used for the skill's primary purpose, they provide the capability to act on malicious instructions injected via the project specifications.
Audit Metadata