The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local documentation files (.md) to audit file paths, symbols, and formatting. This creates an attack surface where malicious instructions embedded in the documentation could potentially influence the agent's behavior during the audit process.
Ingestion points: Documentation files located in docs/best_practices.md and the ./docs/best-practices/ directory.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the documentation being processed.
Capability inventory: The skill uses Edit for file modification and Bash to execute commands such as find, git, and python3.
Sanitization: No sanitization or filtering is performed on the content of the documentation files before processing.
[COMMAND_EXECUTION]: The skill executes a local Python script located at ./script/manage-bp-ids.py with the --validate flag. This execution is part of the intended workflow for validating documentation IDs within the repository's internal environment.

fix-bp-docs