ccdawn-research-rigor-review
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the analysis of external research artifacts, experimental protocols, and results, which constitutes a surface for indirect prompt injection. \n- Ingestion points:
SKILL.mddefines context boundaries that include the processing of 'artifact', 'experimental protocols', and 'data and split'. \n- Boundary markers: There are no defined boundary markers or instructions provided to the agent to disregard instructions that might be contained within the research artifacts. \n- Capability inventory: The skill allows the agent to 'run necessary low-risk re-checks', which may involve executing analysis tools or scripts depending on the agent environment. \n- Sanitization: The skill does not specify procedures for sanitizing or escaping content from external artifacts before processing.
Audit Metadata