research

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest data from untrusted external primary sources, creating a potential surface for indirect prompt injection.
  • Ingestion points: Processes content from external documentation, source code, and APIs (SKILL.md).
  • Boundary markers: Absent; there are no instructions to delimit or ignore instructions within the ingested data.
  • Capability inventory: Includes the ability to write files to the repository (SKILL.md).
  • Sanitization: Absent; no sanitization or validation of external content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 07:05 AM
Security Audit — agent-trust-hub — research