The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the terminal to execute shell commands, including find for filesystem discovery and gh issue create and git push for repository management. These commands are triggered based on data processed from external sources.- [DATA_EXFILTRATION]: By design, the skill pushes documentation and creates issues on GitHub. If manipulated via external content, this mechanism could be used to exfiltrate information from the local environment to an external repository.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Content is retrieved from external URLs using browser_navigate and browser_snapshot in Phase 1 (SKILL.md). Boundary markers: None present; there are no instructions to the agent to treat the fetched content as data rather than instructions. Capability inventory: Includes filesystem searching (find), file writing, GitHub issue creation (gh), and Git operations (git push). Sanitization: None present; extracted content is directly used to generate mapping documentation and populate issue bodies.

field-dev-code-recon