sales-proposal-writer
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill explicitly requires "Discovery notes or call transcript" (SKILL.md) as a primary input for generating the proposal.
- Boundary markers: There are no instructions defining delimiters or explicit instructions for the agent to treat the input data as non-executable text.
- Capability inventory: The skill primarily generates text content for a proposal; it does not contain code for file system modifications, network requests, or subprocess execution.
- Sanitization: No sanitization, filtering, or escaping mechanisms are described to handle potentially malicious content embedded within the discovery notes.
Audit Metadata