ci-all

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to execute a sequence of local development commands. This includes running test suites (pytest, vitest, cargo test), type checkers (tsc), and version control operations (git push). These actions are consistent with the skill's stated purpose of automating a CI pipeline.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external sources and has the capability to modify remote code repositories.
  • Ingestion points: The agent processes output from several CLI tools (pytest, vitest, cargo, git, glab, gh) and user-provided $ARGUMENTS in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or warnings for the agent to ignore potential instructions embedded within the test failures or git logs.
  • Capability inventory: The skill uses the Bash tool to perform git push operations, which can modify the source code or CI configuration on the remote server (GitHub or GitLab).
  • Sanitization: No sanitization or validation of the tool outputs or command arguments is performed before the agent interprets them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:35 AM
Security Audit — agent-trust-hub — ci-all