profile-audit
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing untrusted data from external LinkedIn profiles.
- Ingestion points: LinkedIn profile fields such as Headline, About, and Posts fetched via Apify actors (e.g.,
apimaestro/linkedin-profile-detail). - Boundary markers: Absent. The instructions do not specify delimiters or provide warnings to the agent regarding potential instructions embedded within the external profile content.
- Capability inventory: The agent has the capability to write content to Notion, creating new pages and tables based on the processed data.
- Sanitization: Absent. There are no instructions to validate, filter, or escape content retrieved from the external LinkedIn source before it is interpolated into the audit output.
Audit Metadata