agent-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted task history for analysis. Ingestion points: Task history (SKILL.md). Boundary markers: Absent. Capability inventory: Installation of new skills via npx (SKILL.md). Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill documentation includes references to shell commands for ecosystem management, specifically npx skills add.
- [EXTERNAL_DOWNLOADS]: The skill points to external resources in the fatih-developer/fth-skills repository, which is owned by the skill's author.
Audit Metadata