oban-essentials
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing background job arguments, which serves as an ingestion point for data that could be influenced by external actors.
- Ingestion points: The
perform/1function inSKILL.mdexamples directly pattern-matches and extracts data from theargsfield of the%Oban.Job{}struct. - Boundary markers: There are no instructions or delimiters provided to warn the model about ignoring potential instructions embedded within the job arguments.
- Capability inventory: The skill includes an example in the "Error Handling" section that uses an argument (
url) to perform a network request viaHTTPClient.get(url). - Sanitization: The provided code snippets do not demonstrate validation or sanitization of the arguments before they are used in side-effect producing operations, creating a surface for potential SSRF or parameter injection if the job arguments are user-controlled.
Audit Metadata