The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from git logs and PR descriptions to generate executable artifacts.\n
Ingestion points: The skill reads data from git log --oneline, gh pr list --json title,body, and markdown files in the .agents/handoffs/ directory.\n
Boundary markers: There are no explicit delimiters or instructions provided to the agent to help it distinguish between data to be analyzed and potential instructions embedded within the extracted text.\n
Capability inventory: The skill has access to Bash, Write, and Edit tools, which it uses to create executable hooks in .claude/hooks/, new skills, and rules in CLAUDE.md.\n
Sanitization: No evidence of input validation, escaping, or filtering is present for the content gathered from external sources before it is used in artifact generation.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git and GitHub CLI (gh) commands to gather data from the repository history and remote state. These are standard developer tools and their usage aligns with the skill's primary purpose.

learn