competitive-intel
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file (
.agents/sales-context.md) and user-provided descriptions of competitors. - Ingestion points: The skill explicitly reads
.agents/sales-context.mdand prompts the user for multiple rounds of information regarding competitive landscapes and win/loss patterns. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed data sources.
- Capability inventory: The skill does not use any tools for network operations, file writing, or command execution, significantly limiting the impact of any potential injection.
- Sanitization: No sanitization or validation of the ingested data is performed.
Audit Metadata