agile-intake

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a standard agile workflow tool that gathers user input and formats it into markdown files in the local repository's planning directory. No unauthorized or malicious actions were identified.
  • [PROMPT_INJECTION]: The skill processes user-provided input through the $ARGUMENTS variable, representing a potential surface for indirect prompt injection.
  • Ingestion points: User input provided via the slash command arguments ($ARGUMENTS) in SKILL.md.
  • Boundary markers: No explicit delimitation is used to separate external input from the agent's core instructions.
  • Capability inventory: The skill can perform file system writes to specific paths and trigger other project management skills.
  • Sanitization: No validation or sanitization is performed on the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 07:54 PM