writing-plans

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted user input (requirements/specs) to generate structured plans that include executable shell commands and code blocks.\n
  • Ingestion points: User-provided specifications or requirements in the writing-plans workflow.\n
  • Boundary markers: Absent; the skill does not define delimiters or warnings to ignore instructions embedded within the user's spec.\n
  • Capability inventory: The skill output is designed to be fed into executing-plans or subagent-driven-development, which likely have file-write and shell execution capabilities.\n
  • Sanitization: Absent; the skill does not specify any validation or sanitization of the input requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM