growth-hacking
Warn
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to automatically execute a shell command to scan the user's home directory for other installed AI agent skills upon activation.\n
- Evidence:
ls ~/.claude/skills/ ~/.agent/skills/ ~/.agents/skills/ .claude/skills/ .agent/skills/ .agents/skills/ 2>/dev/null\n- [REMOTE_CODE_EXECUTION]: The skill directs the agent to suggest installing additional dependencies via thenpxpackage runner from an unverified source.\n - Evidence:
npx skills add AbsolutelySkilled/AbsolutelySkilled --skill <name>\n- [EXTERNAL_DOWNLOADS]: The skill promotes the download and installation of tools from 'AbsolutelySkilled', which is not a verified or trusted vendor source.\n - Evidence: Installation instructions point to
AbsolutelySkilled/AbsolutelySkilledand the domainabsolutelyskilled.pro.\n- [PROMPT_INJECTION]: The skill contains instructions that override the agent's standard behavior by forcing automated system checks and mandatory response formatting (emoji usage) immediately upon activation.\n - Evidence: Mandatory requirement to start the first response with the 🧢 emoji and perform an automated
lscheck.
Audit Metadata