competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests data from untrusted external sources and local files. \n
- Ingestion points: Instructions specify reading local context files (
.agents/product-marketing-context.md) and conducting 'Review mining' on third-party sites like G2, Capterra, and TrustRadius. \n - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded prompts within the gathered data. \n
- Capability inventory: The skill is restricted to generating text (URL suggestions, meta tags, and page copy). It does not use subprocesses, file writes, network operations (beyond browser-based research), or code execution. \n
- Sanitization: No sanitization or escaping of external content is defined. Due to the lack of dangerous capabilities, this represents a minimal risk vector.
Audit Metadata