ads-audit
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No evidence of instructions attempting to bypass safety filters or override agent constraints was found.
- [DATA_EXFILTRATION]: While the skill requests advertising account data (exports, screenshots) for analysis, this is consistent with its primary purpose. No patterns of unauthorized network transmission or access to sensitive local files (e.g., SSH keys, AWS credentials) were detected.
- [REMOTE_CODE_EXECUTION]: The skill does not contain any commands for downloading or executing remote scripts or packages.
- [COMMAND_EXECUTION]: There are no shell commands or subprocess calls present in the skill definition. It describes a logic flow rather than executing system-level commands.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or credentials were found. The skill correctly asks for user-provided access or data exports.
- [OBFUSCATION]: The content is written in clear, standard Markdown. No hidden characters, Base64 encoding, or homoglyph-based obfuscation techniques were identified.
Audit Metadata