The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing all markdown files in the repository, which creates an attack surface for indirect prompt injection.
Ingestion points: The skill uses Glob and Read tools to ingest content from every SKILL.md and agent .md file in the project directory.
Boundary markers: There are no explicit instructions to the agent to treat audited file content as data rather than instructions, nor are there delimiters to isolate this content.
Capability inventory: The skill is restricted to file reading tools (Read, Grep, Glob) and does not possess network access or file writing capabilities.
Sanitization: The skill does not implement validation or escaping for the instructions found within the audited files.

ds-audit