Skills
skills/allinherog-star/ai-skills/sop-readability-check/Gen Agent Trust Hub

sop-readability-check

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted external data.
  • Ingestion points: User-provided text in sopProcedureText, uploaded files in sopDocumentFile, and external content from sopReferenceLink defined in references/form-schema.json.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions were found in the provided configuration to delimit untrusted content.
  • Capability inventory: The skill uses scripts/run.py to transmit processed data to an external API (https://ai-skills.ai/api/execute).
  • Sanitization: No evidence of input sanitization or validation was found in the client-side code; processing is likely handled by the remote API.
  • [SAFE]: The network communication identified in scripts/run.py targets the vendor's own infrastructure (ai-skills.ai) and is required for the skill's primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:59 AM
Security Audit — agent-trust-hub — sop-readability-check