feature-radar-validate

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading and processing untrusted data from the workspace.
  • Ingestion points: The scripts/validate.sh script reads content from skills//SKILL.md and .feature-radar/**/.md files.
  • Boundary markers: The validation output does not use delimiters or provide instructions to the agent to ignore embedded commands within the parsed content.
  • Capability inventory: The skill utilizes file-reading commands (cat, awk) and its SKILL.md instructions encourage the agent to perform file-write operations based on the script's output.
  • Sanitization: The script extracts and prints raw string values from the targeted files without sanitization or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:41 AM