Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Tetra Scar Safety
v0.1.0Agent safety that learns from incidents. Reflex arc blocks repeat threats without LLM calls.
⭐ 0· 80·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (learning safety, reflex arc, blocking repeat threats) match the code and SKILL.md. The code implements built-in regex rules, an append-only scar store (safety_scars.jsonl), reflex matching, and CLI/API entry points described in SKILL.md. No unrelated requirements (no cloud creds, no unrelated binaries) are requested.
Instruction Scope
SKILL.md and the code instruct the agent to check actions, record incidents, audit directories, and list scars. This requires reading project files and writing the scar JSONL file; that behavior is coherent with the stated purpose but means the skill will read arbitrary files passed to audit and may persist incident descriptions (which could include secrets) to disk.
Install Mechanism
There is no install spec; the skill is single-file Python and uses only the stdlib. No downloads, third-party packages, or external installers are requested. This minimizes install-time risk.
Credentials
The skill requests no environment variables or external credentials (primaryEnv none). However, it reads filesystem contents during audits and writes an append-only safety_scars.jsonl file in the working directory; those files may contain sensitive information. The requested access is proportional to its purpose but carries privacy risks that the user should consider.
Persistence & Privilege
always:false and normal autonomous invocation are set (no elevated platform privileges). The skill persists scars in an append-only JSONL file (default ./safety_scars.jsonl). That persistent storage is by design but cannot be deleted/modified by the tool and may accumulate sensitive data; the skill does not appear to modify other skills or global agent config.
Assessment
This skill appears to be what it claims: a local safety checker with an append-only incident log. Before installing, consider: (1) audit runs will read files you point it at — do not run audits over root or system directories unless you intend that; (2) safety_scars.jsonl (default ./safety_scars.jsonl) is append-only and may contain incident text that includes secrets or sensitive details — store it with restrictive file permissions, move it to a secure location, or encrypt it if needed; (3) the skill has no network or credential requirements in the provided code, but you should still review the source included in the package before enabling autonomous invocation; (4) for CI/pre-commit use, configure scar file location and retention policy to avoid leaking historical incidents. If you want higher assurance, run the included tests locally and inspect audit/recorded entries to confirm no unexpected behavior.scar_safety.py:99
Dynamic code execution detected.
test_scar_safety.py:136
Dynamic code execution detected.
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk9771sas5p8yzg4455emzfjaj983ayyz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.