Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Panic Prevention Protocol
v1.0.5Prevents panic-driven errors by enforcing a calm, step-by-step recovery process after mistakes or critical feedback to ensure safe, trusted fixes.
⭐ 0· 86·0 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 (prevent panic-driven fixes) match the actual contents: a 9-step protocol, examples, and tests. No binaries, secrets, or unrelated dependencies are requested.
Instruction Scope
SKILL.md and other docs are agent-facing instructions that tell agents to STOP, ASSESS, PLAN, PROPOSE, WAIT, etc. They also explicitly recommend adding protocol text to agent system prompts and installing the skill on all agents. That is coherent with the skill's goal but expands the skill's runtime influence (see persistence_privilege). The docs do not instruct reading secrets, contacting external endpoints, or arbitrary file reads beyond the skill file path.
Install Mechanism
Instruction-only skill with no install spec, no downloads, and no code to execute — minimal install risk.
Credentials
No environment variables, credentials, or config paths are required. The requested scope (policy/protocol text) is proportionate to the stated purpose.
Persistence & Privilege
The skill does not set always:true and is user-invocable. However the documentation recommends adding content to agents' system prompts and installing the protocol across all agents, which increases the skill's behavioral persistence and reach. This is functionally expected for a behavior/policy skill but is a meaningful administrative change that should be applied deliberately and tested in staging.
Scan Findings in Context
[system-prompt-override] expected: The SKILL.md/README explicitly suggests adding protocol text to agent system prompts; the scanner flagged this pattern. This is expected for a behavioral/policy skill, but changing system prompts is a powerful action and can be abused if content is malicious or incorrect.
Assessment
This skill is documentation-only and appears to do what it says: teach agents to pause and follow process after critical feedback. The main operational risk is administrative: the files instruct operators to add protocol text to agents' system prompts and install the skill on all agents. Before deploying widely, do the following: 1) Review the SKILL.md and README content yourself to ensure wording and emergency-path handling meets your policies. 2) Test in a staging environment or on a non-production agent to verify behavior against the included test scenarios. 3) Limit initial rollout to agents that actually need this behavior (e.g., manager/devops agents), not every agent by default. 4) Ensure emergency/active-leak paths are well-defined so urgent incidents aren't blocked by wait steps. 5) Monitor agent logs and approvals after rollout to detect unintended overrides. The scanner's 'system-prompt-override' hit is expected given the installation guidance — treat it as a reminder to audit any system-prompt changes rather than a sign of covert exfiltration.CLAWHUB.md:77
Prompt-injection style instruction pattern detected.
README.md:53
Prompt-injection style instruction pattern detected.
About static analysis
These patterns were detected by automated regex scanning. They may be normal for skills that integrate with external APIs. Check the VirusTotal and OpenClaw results above for context-aware analysis.Like a lobster shell, security has layers — review code before you run it.
latestvk97by8awtzg6pstj33zazk4v0n841g7r
License
MIT-0
Free to use, modify, and redistribute. No attribution required.