glab-schedule
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest and process data from GitLab pipeline schedules (descriptions, variable keys, and values) which may be controlled by untrusted third parties in shared or public repositories.
- Ingestion points: The agent is instructed to use
glab schedule list --output jsonto fetch schedule information from GitLab. - Boundary markers: There are no explicit instructions or delimiters used to warn the agent that schedule descriptions or variables should be treated as untrusted data.
- Capability inventory: The skill includes commands to create, update, delete, and run pipelines, which could be misused if the agent follows instructions embedded in a schedule description.
- Sanitization: No sanitization or validation of the fetched GitLab data is performed before the agent interprets it.
Audit Metadata