board-minutes
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted external data to generate summaries.
- Ingestion points: Step 3 (Agenda and pre-read materials, presentations) and Step 1 (Calendar event details).
- Boundary markers: None identified. The skill does not instruct the agent to ignore instructions embedded within the provided meeting materials.
- Capability inventory: The skill has the capability to read and write files within the
~/.claude/plugins/config/claude-for-legal/directory and perform calendar searches. - Sanitization: No sanitization or validation of the ingested materials is mentioned.
- [COMMAND_EXECUTION]: The skill utilizes a platform-integrated calendar connector to search for upcoming events. While this is a documented feature, it represents an automated interaction with external data services.
- [DATA_EXPOSURE]: The skill explicitly interacts with sensitive corporate data located in
~/.claude/plugins/config/claude-for-legal/corporate-legal/, including board composition, previous minutes, and legal matter specifics. This access is limited to the skill's operational directory and is consistent with its stated purpose as a legal assistant plugin.
Audit Metadata