offer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a potential vector for malicious instructions to influence the agent's behavior.
- Ingestion points: Processes data from user-provided emails, recruitment websites, and screenshots as specified in the workflow of
SKILL.md. - Boundary markers: The instructions do not define boundary markers or explicit prompts for the agent to ignore instructions embedded within the processed recruitment data.
- Capability inventory: The skill has the capability to write HTML files to the user's desktop and utilize a browser to check emails (
SKILL.md). - Sanitization: While the skill correctly advises against writing sensitive information like passwords or MFA codes to public resources, it lacks technical mechanisms to sanitize or escape instructions that might be hidden in the external data sources it reads.
Audit Metadata