pm-lead
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data sources which could contain malicious instructions designed to influence the agent's behavior during report generation.\n- Ingestion points: In SKILL.md, Stage 1 accepts 'raw stakeholder notes, interview transcripts, CRM exports, and support tickets.' Stage 2 accepts 'competitor data and analyst reports.'\n- Boundary markers: The instructions do not specify the use of delimiters or ignore instructions to separate untrusted data from the system prompt.\n- Capability inventory: The skill has the capability to generate and format multiple high-level artifacts, including PRDs, Roadmaps, and Proposals, which are intended for internal and customer-facing use.\n- Sanitization: There is no evidence of sanitization or validation of the ingested raw text before it is processed by sub-skills or used in artifact generation.
Audit Metadata