Skip to main content

agentguard

Enhances AI agent security by blocking dangerous commands and preventing data leaks during code reviews and audits.

Install this skill

or
29/100

Security score

The agentguard skill was audited on Mar 3, 2026 and we found 11 security issues across 4 threat categories, including 2 high-severity. Review the findings below before installing.

Categories Tested

Security Issues

high line 303

Piping content to bash shell

SourceSKILL.md
303| 2025-01-15 14:30 | Bash | rm -rf / | DENY | critical | DANGEROUS_COMMAND | some-skill |
medium line 65

Webhook reference - potential data exfiltration

SourceSKILL.md
65| 20 | WEBHOOK_EXFIL | CRITICAL | all | Webhook exfiltration domains |
medium line 141

Webhook reference - potential data exfiltration

SourceSKILL.md
141**Network Requests**: Check domain against webhook list and high-risk TLDs, check body for secrets
medium line 190

Webhook reference - potential data exfiltration

SourceSKILL.md
190Always combine script results with the policy-based checks (webhook domains, secret scanning, etc.) — the script enhances but does not replace rule-based evaluation.
medium line 275

Access to hidden dotfiles in home directory

SourceSKILL.md
275The audit log is stored at `~/.agentguard/audit.jsonl`. Each line is a JSON object with:
medium line 285

Access to hidden dotfiles in home directory

SourceSKILL.md
2851. Read `~/.agentguard/audit.jsonl` using the Read tool
medium line 339

Access to hidden dotfiles in home directory

SourceSKILL.md
3392. Write the config to `~/.agentguard/config.json`:
medium line 353

Access to hidden dotfiles in home directory

SourceSKILL.md
353When GoPlus AgentGuard is installed as a plugin, it automatically scans all skills in `~/.claude/skills/` at session startup:
medium line 366

Access to hidden dotfiles in home directory

SourceSKILL.md
366This runs asynchronously and does not block session startup. Results are logged to `~/.agentguard/audit.jsonl`.
low line 304

Access to .env file

SourceSKILL.md
304| 2025-01-15 14:28 | Write | .env | CONFIRM | high | SENSITIVE_PATH | — |
high line 51

Access to system keychain/keyring

SourceSKILL.md
51| 6 | READ_KEYCHAIN | CRITICAL | all | System keychain / browser profiles |
Scanned on Mar 3, 2026
View Security Dashboard