skills/mikefilsaime-groove/clickcampaigns-for-claude-code-in-cursor/custom-tasks/Gen Agent Trust Hub
custom-tasks
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- NO_CODE (SAFE): The skill is entirely composed of Markdown text providing quality mandates and formatting standards for marketing tasks. There are no associated scripts (.py, .js, .sh), binaries, or configuration files that perform system-level actions.
- PROMPT_INJECTION (SAFE): While the file uses strong directive language like 'CRITICAL' and 'Mandate', these are used to define the AI's persona and output quality standards. There are no attempts to bypass safety filters, ignore prior instructions, or extract system prompts.
- INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to process 'custom tasks' and 'ad-hoc requests' from users. This represents an ingestion surface for untrusted data. However, since the skill has no functional capabilities (no file writing, no network access, no command execution), the surface is not exploitable beyond influencing the content of the immediate response.
- DATA_EXPOSURE (SAFE): No hardcoded credentials, API keys, or sensitive file paths were found in the skill definition.
Audit Metadata