legal-matter-tracker
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted content from local workspace files to generate reports.
- Ingestion points: The agent scans all .md and .txt files in the workspace root and specific folders like notes/, clients/, and cases/ (specified in SKILL.md).
- Boundary markers: Absent. The instructions in SKILL.md do not specify the use of delimiters or specific safety instructions to isolate file content from the agent's primary task directives.
- Capability inventory: The skill uses the agent's file system capabilities to read workspace files and write summarized reports to the local output/ directory (specified in SKILL.md).
- Sanitization: Absent. The instructions in SKILL.md describe extracting and normalizing dates and facts without specifying validation or escaping of the content.
- [NO_CODE]: This is a no-code skill. It relies entirely on natural language instructions to guide the agent's behavior and does not include any Python scripts, Node.js code, or external binary dependencies.
Audit Metadata