glab-dependency-firewall
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
glabcommand-line utility to interact with GitLab's Dependency Firewall experimental features. This is the core intended functionality provided by the skill. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by processing untrusted data from Dependency Firewall logs.
- Ingestion points: The
ci-summarycommand reads and processes.gitlab/df/ci-log.json(referenced inSKILL.mdandreferences/commands.md). - Boundary markers: The instructions do not define clear delimiters or "ignore instructions" wrappers for the summary data provided to the agent.
- Capability inventory: The skill environment allows command execution (
glab) and local file access within the workspace. - Sanitization: There is no mention of sanitization, filtering, or validation of the log content before it is presented to the agent for summarization.
Audit Metadata