create-doc

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingests untrusted user content from arguments and writes it to a file system accessible to the agent. This content could contain instructions that deceive or manipulate subsequent agent operations when the files are read back.\n
  • Ingestion points: User input provided via $ARGUMENTS is used to generate documentation content in SKILL.md.\n
  • Boundary markers: The skill does not implement delimiters or safety instructions to distinguish between documentation text and potential commands.\n
  • Capability inventory: The skill utilizes the Read, Glob, and Write tools to interact with the local .chalk/docs/ directory.\n
  • Sanitization: No sanitization or validation of the documentation content is performed before the file is written to the disk.- [SAFE]: The skill operates entirely within the local environment using standard file system tools. There are no indications of external network calls, hardcoded credentials, or malicious obfuscation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 11:36 AM