Commute Matrix
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection when processing external data from camp provider files. If these files contain malicious instructions, the agent might follow them when generating summaries or recommendations.\n
- Ingestion points: Provider markdown files located in
<research_dir>/providers/*.md, as processed inSKILL.md(Step 2) andscripts/commute_calculator.py(scan_providers function).\n - Boundary markers: The skill instructions do not define delimiters or provide 'ignore embedded instructions' directives to isolate external content.\n
- Capability inventory: The agent is tasked with generating recommendations and updating local markdown files based on the processed data, as seen in
SKILL.md(Steps 4 and 5) andscripts/commute_calculator.py(update_provider_files function).\n - Sanitization: While the Python script uses regex to extract specific fields, it does not sanitize the resulting strings to prevent them from being interpreted as instructions by the agent.
Audit Metadata