recoup-internal-consulting-call-processor
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data (meeting transcripts, notes, and emails) which could contain malicious instructions designed to manipulate the agent's behavior during the extraction and filing process.
- Ingestion points: Reads raw file content from transcripts, meeting notes, and emails as described in steps 2 and 3.
- Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill has the ability to write to local project files (e.g., AGENTS.md, dashboard.html) and trigger multiple sibling workflow skills.
- Sanitization: No sanitization or validation of the input text is mentioned before it is used to update dashboards and knowledge bases.
Audit Metadata