The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to execute a local Python script (audit-docs.py) located in a related skill's directory. This command is used to verify the integrity of links within the documentation.
Evidence: python3 <docs-governance-skill>/scripts/audit-docs.py --root <repository> --scope modules --module <module-directory> (SKILL.md)
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the project environment, which presents a surface for indirect prompt injection attacks.
Ingestion points: The agent is instructed to read project instructions, mapping documents, requirements, source code, and contracts (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers when reading these external files.
Capability inventory: The skill can read project files, write/update local instruction files (AGENTS.md, CONTEXT.md), and execute the audit-docs.py script.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content read from external files before it is used to influence the agent's documentation updates.

module-governance