citation-claim-audit
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is purely instructional and organizational.
- [PROMPT_INJECTION]: The skill instructions involve processing external research materials such as PDFs and bibliography records. This represents an ingestion surface for untrusted data (Indirect Prompt Injection). However, the skill does not define or use any high-risk capabilities like arbitrary command execution or network exfiltration. Ingestion points: SKILL.md (PDFs, artifacts) and references/output-contracts.md (sources/pdfs, data/raw/). Boundary markers: absent. Capability inventory: none (no scripts or external tools provided). Sanitization: absent.
Audit Metadata