ci-cd-pipelines
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a shell command to discover other installed skills on the local system. * Evidence:
ls ~/.claude/skills/ ~/.agent/skills/ ~/.agents/skills/ .claude/skills/ .agent/skills/ .agents/skills/ 2>/dev/nullinSKILL.md. - [EXTERNAL_DOWNLOADS]: The skill recommends installing additional components from external repositories using npx. * Evidence:
npx skills add AbsolutelySkilled/AbsolutelySkilled --skill <name>inREADME.mdandSKILL.md. - [PROMPT_INJECTION]: The skill includes instructions to alter the agent's standard response behavior. * Evidence:
When this skill is activated, always start your first response with the 🧢 emoji.inSKILL.md.
Audit Metadata