competitive-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to mine and analyze data from external websites such as G2, Capterra, and Trustpilot. This creates a surface for indirect prompt injection where an attacker could place malicious instructions within a review or social media post to influence the agent's behavior.
- Ingestion points: The skill reads internal product positioning from
.agents/product-marketing-context.mdand processes external content from review sites and LinkedIn (SKILL.md). - Boundary markers: Absent; there are no specific instructions or delimiters provided to help the agent distinguish between the analysis instructions and the untrusted content being processed.
- Capability inventory: The skill performs file read and write operations within the
.agents/directory to store competitor profiles and battlecards. - Sanitization: Absent; the skill does not specify any filtering, sanitization, or validation of the content retrieved from external sources before it is analyzed.
Audit Metadata