find-b2b-creators-linkedin
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for influencer marketing analysis. There are no scripts, binaries, or automated commands provided that could lead to unauthorized actions.
- [PROMPT_INJECTION]: The instructions require the agent to ingest and evaluate external data, specifically comments on LinkedIn posts. This creates a surface for indirect prompt injection, where an attacker could place malicious instructions within a comment to attempt to manipulate the agent's vetting process.
- Ingestion points: LinkedIn comments and post content are designated as input for creator evaluation (SKILL.md).
- Boundary markers: There are no instructions for the agent to use delimiters or ignore embedded commands when processing external text.
- Capability inventory: The skill does not request file-system writing, network exfiltration, or shell execution capabilities.
- Sanitization: No sanitization or validation steps are prescribed for the external content before it is processed by the agent.
Audit Metadata