prompt-templates

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it is designed to ingest and process untrusted external data within structured AI prompts.
  • Ingestion points: The skill processes user-supplied data through variables such as 'line_items', 'schedule_data', 'clash_data', and 'spec_text' defined in the SKILL.md templates.
  • Boundary markers: The prompt templates interpolate user data directly into the prompt string without using explicit delimiters (e.g., XML tags or triple quotes) or specific 'ignore embedded instructions' warnings.
  • Capability inventory: The agent is granted filesystem permissions via claw.json, enabling it to read local files which may contain malicious instructions.
  • Sanitization: The implementation logic in SKILL.md demonstrates a best practice by using Python's string.Template.safe_substitute for variable interpolation, which prevents basic formatting-based injection attacks during the construction of the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:28 AM