ptlam-testing
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands to run test suites at multiple levels (unit, integration, and end-to-end) and report the exact commands and outcomes to the user (SKILL.md, references/workflows/test-driven-development.md).
- [EXTERNAL_DOWNLOADS]: The environment resolution workflow instructs the agent to research and recommend testing tools from official registries and SDK documentation when the current toolchain is insufficient. The skill requires the agent to obtain user confirmation before adding or replacing project dependencies (references/workflows/resolve-testing-environment.md).
- [PROMPT_INJECTION]: The skill ingests untrusted repository content, including production code, manifests, and existing tests, to resolve project context and audit test quality. This creates a surface for indirect prompt injection where malicious content in the codebase could attempt to influence the agent's behavior.
- Ingestion points: Reads manifests, lockfiles, build configurations, and source code across the project root (SKILL.md, references/workflows/resolve-project-testing-context.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes file content.
- Capability inventory: The agent has the ability to write to the filesystem (creating CONTEXT.md and test files), execute shell commands (running tests), and propose dependency modifications.
- Sanitization: No specific sanitization or filtering logic is defined for the ingested project data.
Audit Metadata