weekly-report-writer
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, such as credential theft or remote code execution, were detected. The skill's primary function is to process local Markdown documents within a user-provided directory.\n- [DATA_EXFILTRATION]: The skill does not perform any network operations (like curl or wget) and lacks instructions to send data to external domains. Information synthesis occurs entirely within the agent's local environment.\n- [PROMPT_INJECTION]: The skill defines clear logic for report synthesis (linking tracking, task status identification, and inheritance) without any instructions aimed at bypassing agent safety filters or overriding system instructions.\n- [DATA_EXPOSURE]: The skill accesses local file paths provided by the user to read notes. This behavior is transparently described in the workflow and involves human confirmation of the file list (Step 3), ensuring the agent only accesses intended content.
Audit Metadata