hiring-manager-msg
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's behavior is consistent with its stated purpose of drafting professional outreach messages.
- [DATA_EXPOSURE]: The skill reads from local files such as
search/context/experience-library.yamlandsearch/intel/{company-slug}.yaml. This is legitimate access to provide the agent with the necessary context for personalized writing. - [PROMPT_INJECTION]: The skill utilizes
WebSearchandWebFetchto research company blogs and LinkedIn profiles. This constitutes an indirect prompt injection surface where untrusted external content could influence the agent's output. - Ingestion points: Research results from
WebSearchandWebFetchfor company and hiring manager details. - Boundary markers: None identified in the prompt instructions to delimit untrusted web content.
- Capability inventory: The skill has the ability to write files to the
search/vault/generated/outreach/directory. - Sanitization: No explicit sanitization or validation of the retrieved web content is performed before interpolation into the drafted message.
Audit Metadata