research
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a research tool designed to collect information from documentation and source code. No indicators of malicious command execution, data exfiltration, or obfuscation were found. The attribution to an upstream repository is documented neutrally.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external primary sources, creating a surface for indirect prompt injection. The potential impact is limited as the skill's capabilities are restricted to writing Markdown reports to the local repository.
- Ingestion points: External primary sources (official docs, source code, specs, APIs) defined in
SKILL.md. - Boundary markers: Absent.
- Capability inventory: Repository file-write access for Markdown notes defined in
SKILL.md. - Sanitization: None specified.
Audit Metadata