skills-audit
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by reading and analyzing the content of other installed skill files (
SKILL.md) located in the user's global and project skill directories. This ingestion of external data constitutes a surface for indirect prompt injection. - Ingestion points: Reads files from
~/.claude/skills/and.claude/skills/to collect metadata and analyze instructions. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore potential commands embedded within the audited skill files.
- Capability inventory: The skill is restricted to data collection and analysis; it lacks capabilities for network communication, arbitrary command execution, or file modification.
- Sanitization: The skill does not specify sanitization or escaping of audited content before it is presented in the final report.
Audit Metadata