atv-security
atv-security is an Application security skill for AI agents, published by All-The-Vibes in the ATV-StarterKit repository on GitHub. Skillspace rates atv-security F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
Unified ATV security audit. Scans agentic config (.github/, .vscode/) using AgentShield's 33-rule taxonomy AND application source code for OWASP Top 10 + STRIDE threats. Triggers on 'security scan', 'audit security', 'check config security', 'atv-security', 'security audit', 'scan for vulnerabilities', 'cso', 'owasp scan', 'threat model', 'stride analysis', 'application security', 'security review code'.
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 46
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 87 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Critical-risk patterns
- License
- MIT
- Adoption
- Adopted by 3 other repositories, in 0 collections
What the scanner flagged
- pipe remote script to shell
- prompt-injection: ignore-previous
- exfiltration language
- references sensitive credential env
- accesses sensitive system files
- executes shell/subprocess
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.