competitive-intel
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill does not contain any code, obfuscation, or direct command execution patterns. It functions as a prompt template for sales strategy.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from project files, which constitutes a potential vulnerability surface. 1. Ingestion points: The file
.agents/sales-context.mdis read to extract value propositions and differentiators. 2. Boundary markers: Absent; there are no explicit delimiters or instructions to the agent to ignore embedded commands within the ingested file. 3. Capability inventory: No risky capabilities such as subprocess calls, network operations, or file-write commands are present in the skill's instructions. 4. Sanitization: None; external content is interpolated directly into the agent's logic for positioning.
Audit Metadata