aya-source-investigation
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external sources during its fact-checking process, which constitutes a potential indirect prompt injection surface.\n
- Ingestion points: Search results and third-party web content as specified in SKILL.md.\n
- Boundary markers: No explicit delimiters or ignore instructions for the fetched content.\n
- Capability inventory: Limited to browsing and information retrieval; no subprocess, file-write, or network exfiltration capabilities associated with the ingested data.\n
- Sanitization: Instructions to paraphrase findings and limit direct quotations help mitigate risks.\n- [EXTERNAL_DOWNLOADS]: The documentation includes a link to a GitHub repository (github.com/N0zoM1z0/gensokyo-monochrome-heart) to explain the character-to-workflow mapping. This is a reference to a well-known service and belongs to the identified skill author context.
Audit Metadata