test-tag-pipeline
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes user input and interpolates it directly into bash command strings. This creates a potential vulnerability surface where malicious input could lead to command injection if the scripts are not robust.
- Ingestion points: User arguments
tag-nameandbranch-specare passed into the skill via{{args.0}}and{{args.1}}placeholders inSKILL.md. - Boundary markers: Absent. The skill does not use delimiters or instructions to prevent the agent from interpreting embedded commands within the user input.
- Capability inventory: The skill executes shell scripts located in
hack/tools/scripts/usingbashand performs operations using theocCLI tool. - Sanitization: Absent. The instructions do not include steps to validate, escape, or filter the user-provided data before passing it to the command-line interface.
Audit Metadata