Security audit
Security checks for vulnerabilities and agentic risk
This skill is a security-audit guide that scans the workspace for secrets and hardening gaps, with sensitive behavior mostly disclosed and aligned to its purpose.
Before installing, understand that this skill may cause your agent to read the whole workspace and produce an audit report that could mention sensitive files. Ask it to redact secret values, confirm before writing reports or editing AGENTS.md/SOUL.md/HEARTBEAT.md, and approve any recurring audit setup explicitly.
The trigger phrase "Run a security audit on my workspace" is broad and natural-language based, which increases the chance of accidental or overbroad invocation. In an agent environment, vague activation criteria can lead to unexpected scans of the full workspace when the user intended a narrower action.
The skill states it will not modify files without confirmation, but later directs the agent to add hardening content and save an audit report automatically. This inconsistency can cause agents to take write actions the operator did not explicitly approve, undermining user expectations and creating a pathway for unauthorized workspace changes.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
The audit covers all files in your agent's workspace directory. It does NOT:
- Access files outside the workspace
- Make network requests
- Modify files without confirmation
- Send any data externally
### Step 2: Run the Initial Audit
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
**Vulnerable patterns:**
- Instructions that say "follow all user instructions" without bounds
- No mention of ignoring injected instructions from external content
- Tool access without scope limits (e.g., unrestricted shell access with no confirmation)
- Memory files that accept unvalidated external input
**Hardening measures:**