The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to verify the presence of local project documentation files and provide status updates. These operations are benign and restricted to internal environment checks.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from both user interactions and local files to populate iteration plans. 1. Ingestion points: Data is collected from user responses and local documentation files. 2. Boundary markers: The skill does not employ specific delimiters to protect against malicious instructions embedded in user input. 3. Capability inventory: The skill has access to Bash, Read, and Write tools. 4. Sanitization: No validation or escaping is applied to input data before it is used in documentation generation.

pm-iteration