setup
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from resumes and LinkedIn CSV exports which may contain embedded instructions designed to influence the agent's behavior.
- Ingestion points: Resume upload (Step 1) and LinkedIn CSV upload (Step 3) in
SKILL.md. - Boundary markers: The skill does not use specific delimiters or instructions to ignore commands within these documents.
- Capability inventory: The skill utilizes file system read and write permissions within the
~/.proficiently/directory to store and manage collected data. - Sanitization: No content validation or sanitization is performed on the ingested files before processing by the agent.
Audit Metadata