competitive-roadmap-review
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, including competitor reports and customer call transcripts, creating a surface for indirect prompt injection attacks where adversarial instructions could be embedded in the data.
- Ingestion points: Customer call intelligence, win/loss research, and competitor market evidence as specified in SKILL.md and references/INTERNAL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the logic.
- Capability inventory: The skill focuses on analytical reasoning and reporting; it lacks dangerous capabilities like arbitrary shell command execution or unauthorized network access.
- Sanitization: No explicit sanitization or filtering logic is defined for the ingested external content.
Audit Metadata