linkedin-influencer-discovery
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes influencer data retrieved from an external database, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Data is ingested from the Apify dataset API within
scripts/discover_influencers.py(line 86). - Boundary markers: The skill does not implement delimiters or specific instructions to the agent to disregard instructions potentially embedded in biography or topic fields.
- Capability inventory: The skill uses the
requestslibrary to communicate with the Apify and Gooseworks APIs. - Sanitization: External content, such as influencer biographies, is outputted to the agent without sanitization or filtering.
Audit Metadata