skill-status
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts and displays content from
SKILL.mdfiles found in both core plugin and project-local directories to generate its inventory report. This ingestion of external file content into the agent context constitutes a potential injection surface. - Ingestion points: Reads frontmatter and description fields from
SKILL.mdfiles located in~/.claude/plugins/cache/bkit-marketplace/bkit/*/skills/and.claude/skills/project/*/SKILL.md. - Boundary markers: Absent; the skill parses and reproduces text from these files directly into the terminal output.
- Capability inventory: The skill uses
Bash,Read,Glob, andGreptools to locate files and extract specific lines of text. - Sanitization: There is no evidence of filtering or sanitizing the content read from the external
SKILL.mdfiles before displaying them to the user.
Audit Metadata