tdd-ci
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to detect the project stack, validate generated YAML, and commit changes. Specifically, it uses
git,npm,npx,pytest, and the GitHub CLI (gh). It also provides commands to interact directly with the GitHub API for repository management. - [PRIVILEGE_ESCALATION]: The skill provides instructions and specific command-line examples for modifying repository branch protection rules via the GitHub API (using
gh api -X PUTandgh api -X DELETE). These operations allow for the modification of significant security policies that govern how code is merged into the main branch. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from the local filesystem to drive its automation.
- Ingestion points: The skill reads
package.json,Makefile,requirements.txt, and other project metadata to determine test commands and directory structures (SKILL.md, Step 1). - Boundary markers: The instructions do not define specific boundary markers or delimiters to isolate data extracted from these files from the logic used to generate the workflow YAML.
- Capability inventory: The skill has the capability to write files to
.github/workflows/, execute shell commands, perform git commits, and modify repository settings through the GitHub API. - Sanitization: There is no mention of sanitizing or validating strings extracted from project files before they are interpolated into the GitHub Action templates.
Audit Metadata