paper-code-audit
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates auditing research papers and codebases, creating a surface for indirect prompt injection from processed data. 1. Ingestion points: Academic papers and public codebases provided by the user or fetched from URLs (SKILL.md). 2. Boundary markers: None specified to delimit external content or warn the agent. 3. Capability inventory: No executable scripts or tool-use capabilities are defined within this skill file. 4. Sanitization: No sanitization or validation of the external content is mentioned.
- [NO_CODE]: The skill consists of a single markdown file with instructions and does not include any executable scripts or configuration files.
Audit Metadata