The Agent Skills Directory

[SAFE]: The skill's primary function is to analyze existing documentation (READMEs, API specs, guides) within a local repository to produce a curated map for AI answer engines. This process follows established best practices for project discoverability.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection as it ingests untrusted data from the analyzed repository. However, the risk is minimal given the skill's specific purpose of summarizing documentation rather than executing content.
Ingestion points: The skill scans numerous file types including README.md, content in the docs/ directory, OpenAPI specifications, and other repository metadata as described in Step 1 of the procedure in SKILL.md.
Boundary markers: The instructions do not specify explicit boundary markers or directives to ignore embedded instructions within the source files during the scanning process.
Capability inventory: The skill is capable of writing generated files (llms.txt and llms-full.txt) to the repository root, as outlined in Step 7 of SKILL.md.
Sanitization: The instructions do not include specific sanitization or escaping protocols for the content extracted from repository files before it is included in the final generated output.

llms-txt