02-profile-audit
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from LinkedIn profiles (About sections, experience descriptions, and posts). Malicious instructions embedded in a profile could potentially influence the agent's audit logic.
- Ingestion points: LinkedIn profile content retrieved via external tools such as
apimaestro/linkedin-profile-detailandapimaestro/linkedin-profile-posts. - Boundary markers: Absent. There are no delimiters or explicit instructions for the agent to treat the imported profile content as untrusted data.
- Capability inventory: The skill invokes tools to fetch web content and has the ability to write new pages to a Notion workspace.
- Sanitization: Absent. There is no evidence of filtering or escaping applied to the LinkedIn profile text before it is processed by the model.
- [EXTERNAL_DOWNLOADS]: The skill utilizes external tools on the Apify platform to retrieve profile data and interacts with the Notion API for storing results.
Audit Metadata