pr-strategist
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override system behavior, bypass safety filters, or extract system prompts were detected. The instructions are clearly scoped to the PR strategist role.
- [DATA_EXFILTRATION]: The skill does not access sensitive local file paths (such as .ssh or .aws directories) and performs no unauthorized network requests. All data processing is instructional rather than operational.
- [REMOTE_CODE_EXECUTION]: There is no evidence of remote script execution, package installation (pip/npm), or dynamic code evaluation (eval/exec).
- [DYNAMIC_CONTEXT_INJECTION]: The skill does not utilize the
!commandsyntax or other mechanisms to execute shell commands during the initialization phase. - [EXTERNAL_DOWNLOADS]: While the skill mentions legitimate external PR platforms (e.g., Qwoted, Featured.com, Hacker News) as resources for the user to engage with manually, it does not programmatically fetch or execute content from these or any other external domains.
Audit Metadata