goal-definition

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from project documentation (context-map.md) and user-supplied requests to generate its output. Without sanitization, malicious instructions embedded in these sources could influence the agent's behavior.
  • Ingestion points: context-map.md and raw user request strings.
  • Boundary markers: No specific delimiters or safety instructions are used to isolate untrusted data during processing.
  • Capability inventory: The skill performs local file read operations and writes a specific Markdown file (goal-definition.md) to the filesystem.
  • Sanitization: No input validation or escaping is performed on the ingested content before it is interpolated into templates.
  • [NO_CODE]: The skill consists entirely of Markdown instructions and reference templates. It does not contain any executable scripts, binaries, or automated installation steps, which significantly limits the potential for direct code-based attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:09 PM