jk
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its interaction with untrusted external data from Jenkins controllers combined with significant administrative capabilities.
- Ingestion points: The agent ingests external content from Jenkins controllers through commands like
jk log(reading console output),jk job config(reading XML configurations), andjk search(reading build and job metadata). - Capability inventory: The skill possesses broad administrative capabilities, including updating job configurations (
jk job configure), creating new jobs (jk job create), managing credentials (jk cred create-secret), and installing plugins (jk plugin install). - Boundary markers: There are no defined boundary markers or specific instructions to the agent to treat data from the Jenkins controller as untrusted or to ignore embedded instructions within that data.
- Sanitization: No sanitization or validation logic is specified for the data retrieved from Jenkins before it is incorporated into the agent's context and used to inform further actions.
Audit Metadata