corporate-vp
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input such as business scenarios and strategic documents, and has the capability to output to external organizational systems.
- Ingestion points: Ingests user-provided organizational context, strategic queries, and potentially uploaded business documents as specified in
SKILL.md. - Boundary markers: Lacks explicit delimiters or instructions to prevent the agent from following commands that might be embedded within the analyzed business data.
- Capability inventory: Interactions with project management tools (Jira, Linear), document storage (Notion, Google Drive), and communication tools (Slack) are mentioned in the operating context of
SKILL.md. - Sanitization: No validation or sanitization mechanisms are defined to handle or escape potentially malicious instructions present in the processed data.
Audit Metadata