review

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted code provided via the $ARGUMENTS variable without sufficient isolation markers.
  • Ingestion points: Untrusted data enters the agent context through the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: The prompt lacks explicit delimiters or instructions to treat the ingested content as data only, which could allow embedded instructions to override the agent's behavior.
  • Capability inventory: No dangerous capabilities such as network access, file system modifications, or subprocess execution were identified.
  • Sanitization: There is no evidence of input sanitization or filtering to mitigate malicious content in the input code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 09:50 AM