skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/meeting-minutes-generator/Gen Agent Trust Hub
meeting-minutes-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources to generate reports.
- Ingestion points: The skill accepts project data through CSV, Excel, and JSON files, or direct user input as specified in instructions.md.
- Boundary markers: The instructions lack explicit boundary markers or delimiters to separate user-provided data from system instructions, nor do they include warnings for the agent to ignore embedded commands within the data.
- Capability inventory: The skill possesses filesystem permissions as defined in claw.json and utilizes the pandas library in SKILL.md to write data to the local disk via the to_excel method.
- Sanitization: There is no evidence of text sanitization, filtering, or validation logic to prevent malicious payloads embedded in meeting topics or action items from influencing the agent's behavior.
Audit Metadata