ptlam-health-connector-review
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard development tools including version control (
git), monorepo management (melos), and language-specific toolchains (dart,gradlew,swift). These commands are necessary for the skill's functionality, such as analyzing changes and running linters or tests. The instructions include specific constraints preventing unauthorized file modification or the execution of rewriting commands during the review process. - [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data in the form of code diffs and file contents. However, the instructions are highly specific, focusing the agent on reporting findings rather than executing instructions found within the code. The skill also enforces architectural boundaries and layer ownership, which further limits the impact of potentially malicious content in the reviewed code.
Audit Metadata