The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of external repository files.
Ingestion points: The skill reads AGENTS.md, DEVELOPMENT.md, package.json, and various project source files to gather context (SKILL.md).
Boundary markers: The instructions do not define clear delimiters or provide warnings for the agent to ignore instructions embedded in the data being audited.
Capability inventory: The skill allows the agent to read and edit files, and execute shell commands via mise and git.
Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the agent.

audit-simplification