The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands to inspect local directory structures and verify file existence as part of its auditing workflow.
Evidence: The Analysis Workflow in SKILL.md (Step 1) uses ls -la to validate target skill paths.
Evidence: The utility script scripts/extract-yaml.sh uses sed to extract frontmatter content from files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and evaluate content from external SKILL.md files, which represents a surface for processing untrusted data.
Ingestion points: The skill accepts user-provided paths to local skill directories and reads the SKILL.md file in SKILL.md (Step 1).
Boundary markers: Absent. The skill instructions do not specify delimiters or instructions for the agent to ignore embedded commands within the files being audited.
Capability inventory: Execution of basic shell commands (ls), file system read access, and the ability to write report files to the current working directory.
Sanitization: Absent. The helper scripts (scripts/extract-yaml.sh and scripts/skill-audit.py) perform direct extraction and regex-based analysis without security-focused sanitization.

skill-quality-reviewer