linkedin-algorithm
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze user-provided data (90 days of LinkedIn posts) which presents an attack surface for indirect instructions.
- Ingestion points: LinkedIn post content, metrics, and metadata analyzed during the Phase 1 diagnosis in
SKILL.md. - Boundary markers: None identified; the instructions do not specify how to distinguish post content from potential embedded commands.
- Capability inventory: The agent is authorized to execute the included
scripts/check-output.pyand has general file-handling capabilities to create the audit deliverable. - Sanitization: No sanitization or filtering of the ingested post data is prescribed.
Audit Metadata