create-plan

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to read and follow conventions from external files such as 'AGENTS.md' and files within '.chalk/.cursor/plans/'. This creates an indirect prompt injection surface where a malicious actor who can modify these files could potentially influence the agent's output or behavior during the plan creation process.
  • Ingestion points: Reads from 'AGENTS.md' and the '.chalk/.cursor/plans/' directory.
  • Boundary markers: None specified in the instructions to distinguish between trusted instructions and data from these files.
  • Capability inventory: Uses 'Read', 'Glob', and 'Write' tools to manipulate the file system.
  • Sanitization: No evidence of sanitization or validation of the content retrieved from these external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 11:36 AM