rk-idea
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content which may contain malicious instructions.
- Ingestion points: The skill reads the 'active paper' from the request, the working directory, and project-specific instruction files like
AGENTS.md(as specified inSKILL.md). - Boundary markers: The instructions do not specify the use of clear delimiters or 'ignore embedded instructions' warnings when processing these external files.
- Capability inventory: The skill has the capability to 'change files' within the active paper's directory (as mentioned in the 'Active paper' section of
SKILL.md). - Sanitization: There is no explicit requirement for the agent to sanitize or filter instructions found within the processed scientific notes or
AGENTS.mdfiles.
Audit Metadata