tekton-pipelines

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting untrusted or external data into a high-capability execution environment (Tekton CI/CD).
  • Ingestion points: Found in SKILL.md via params.repo-url, matrix parameter substitution, and Common Expression Language (CEL) expressions processing body payloads.
  • Boundary markers: Absent; no specific delimitation or 'ignore instructions' warnings are provided for these interpolation points.
  • Capability inventory: The environment supports arbitrary shell execution via script blocks and remote resource fetching via git and hub resolvers.
  • Sanitization: No input validation or sanitization logic is described for the external parameters.
  • [EXTERNAL_DOWNLOADS]: The skill documents the use of Tekton resolvers to fetch pipeline components from external repositories.
  • Evidence: SKILL.md demonstrates fetching task YAML from repositories via the git resolver using the taskRef mechanism.
  • [COMMAND_EXECUTION]: The skill includes examples of executing shell commands within the context of a pipeline step.
  • Evidence: A script block in SKILL.md performs a git clone operation using a parameter-driven URL.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 07:24 PM