hl-discover
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse and summarize data from untrusted repositories, including READMEs, manifests, and source code. This exposure to external, attacker-controlled content creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill reads README files, project manifests, and source code as described in the SKILL.md.
- Capability inventory: The skill uses git commands and has the ability to delegate tasks to subagents.
- Boundary markers: There are no explicit instructions to use delimiters or security warnings when outputting data derived from untrusted repository files.
- Sanitization: The skill does not describe any sanitization or validation of the text read from the repository before processing or summarizing it.
Audit Metadata