Skip to main content

vigil

Provides safety guardrails for AI agents, validating tool calls to prevent destructive actions and enhance security.

Install this skill

or
0/100

Security score

The vigil skill was audited on Feb 16, 2026 and we found 9 security issues across 4 threat categories, including 3 critical. Review the findings below before installing.

Categories Tested

Security Issues

critical line 46

Eval function call - arbitrary code execution

SourceSKILL.md
46- Encoding attacks (base64 decode, eval(atob())) → BLOCK
critical line 44

Access to /etc/shadow

SourceSKILL.md
44- Path traversal (../../../etc/shadow) → BLOCK
high line 44

Path traversal pattern

SourceSKILL.md
44- Path traversal (../../../etc/shadow) → BLOCK
critical line 42

Access to SSH directory

SourceSKILL.md
42- Data exfiltration (curl to external, .ssh/id_rsa access) → BLOCK
medium line 46

Base64 decode operation

SourceSKILL.md
46- Encoding attacks (base64 decode, eval(atob())) → BLOCK
medium line 46

Base64 decode via atob()

SourceSKILL.md
46- Encoding attacks (base64 decode, eval(atob())) → BLOCK
low line 19

External URL reference

SourceSKILL.md
19- **npm:** https://www.npmjs.com/package/vigil-agent-safety
low line 102

External URL reference

SourceSKILL.md
102- npm: https://www.npmjs.com/package/vigil-agent-safety
low line 103

External URL reference

SourceSKILL.md
103- Docs: https://hexitlabs.com/vigil
Scanned on Feb 16, 2026
View Security Dashboard
Installation guide →
GitHub Stars 2.2K
Rate this skill
Categorydevelopment
UpdatedApril 10, 2026
openclaw/skills