sales-proposal-generator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes meeting transcripts and sales briefs which are untrusted external inputs. This creates a surface for indirect prompt injection where instructions hidden in the text could attempt to manipulate the agent's output or tool usage.\n
- Ingestion points: Discovery call transcripts and sales briefs (SKILL.md).\n
- Boundary markers: The instructions lack explicit delimitation for the input materials.\n
- Capability inventory: The agent can generate documents and execute a local validation script.\n
- Sanitization: Instructions include rules for grounding claims in authorized sources and sanitizing file paths.\n- [COMMAND_EXECUTION]: The skill executes a bundled script (scripts/validate-formatting.js) to inspect DOCX files using the system's unzip utility.\n
- Execution method: The script is called via Node.js and uses execFileSync to run the unzip command.\n
- Mitigation: The skill specifies that filenames should be sanitized and path separators avoided.
Audit Metadata