The Agent Skills Directory

[SAFE]: No security vulnerabilities were detected. The skill performs legitimate diagnostic and reporting functions within its stated scope.
[INDIRECT_PROMPT_INJECTION]: The skill inherently processes repository data (commit logs and project files) to identify patterns. While this presents a potential surface for indirect prompt injection, the risk is mitigated by the restricted set of allowed tools (git log, uds audit) and the absence of high-risk capabilities like arbitrary shell execution or broad network access.
Ingestion points: Project files in .standards/ and commit history via git log in SKILL.md.
Boundary markers: Not explicitly defined in the instructions.
Capability inventory: Read, Grep, Glob, and restricted Bash commands listed in the YAML frontmatter.
Sanitization: Not specified in the instruction markdown.

audit