find-jobs-boards
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external websites and has the capability to write to the local filesystem.
- Ingestion points: External job board data is fetched using the
WebFetchtool as part of the job enumeration process inSKILL.md. - Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions when processing fetched web content.
- Capability inventory: The skill can use the
Writetool to save data to the filesystem and theBashtool to create directories. - Sanitization: Absent; no specific sanitization, validation, or filtering of the fetched content is required before the agent formats and writes it to the output file.
Audit Metadata