ia-format

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as it processes untrusted data from external files or user input.
  • Ingestion points: The skill reads content from file paths or text blocks provided via $ARGUMENTS in SKILL.md.
  • Boundary markers: There are no delimiters or instructions defined to prevent the agent from following malicious instructions that might be embedded in the content being formatted.
  • Capability inventory: The skill performs file write operations (overwriting files) across the workspace as described in SKILL.md.
  • Sanitization: No sanitization or validation of the input text is specified before the formatting process begins.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 06:41 PM
Security Audit — agent-trust-hub — ia-format