ai-slop-audit
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and analyze untrusted external content (proposal artifacts and third-party sources), which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill reads proposal artifacts and sources for factual claims provided by users or external registers (SKILL.md).
- Boundary markers: The instructions lack explicit guidance on using delimiters or boundary markers to isolate the audited content from the system instructions, increasing the risk that the agent may follow instructions embedded within the artifact.
- Capability inventory: The skill defines a capability contract allowing for network checks to verify claims, which could be abused if an injection attack succeeds (SKILL.md).
- Sanitization: No instructions are provided for sanitizing or filtering external content before analysis.
Audit Metadata