The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions involve executing a local script fdk/tools/skill-provenance.py via python3. These commands are used to perform administrative tasks such as recording skill metadata, calculating checksums, and performing integrity checks during Continuous Integration (CI) workflows.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it reads and processes all files within individual skill directories (skills/<name>/) to calculate SHA256 checksums.
Ingestion points: Files located within the skills/ directory structure are read during the check and record operations.
Boundary markers: Not explicitly defined in the provided markdown instructions.
Capability inventory: The skill utilizes local script execution and file system read/write access (specifically writing to fdk/skills.provenance.json).
Sanitization: Not specified, as the primary operation is cryptographic hashing for integrity verification.

skill-provenance