The Agent Skills Directory

[SAFE]: The skill is configured with a restricted set of tools (Read, Glob, Grep) in SKILL.md, limiting its operations to local file analysis without network or modification capabilities.
[DATA_EXPOSURE]: The skill accesses project files, including design documents and sprint history, which is necessary for its stated purpose of historical analysis and complexity estimation. This access is restricted to the local filesystem.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from task descriptions (user arguments) and project files (codebase and sprint data) without explicit boundary markers or sanitization. However, the capability inventory is strictly limited to read-only operations, preventing any malicious code execution or data exfiltration.

estimate