MiroFish is an AI agent skill, created by 666ghj and published at 666ghj/MiroFish. ClawSecure audited MiroFish across 69 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 80/100 (Safe). The 4 findings concentrate in ReDoS and Permissions Manifest, including Missing config.json - agent may not be properly configured and ReDoS vulnerability: Nested quantifiers (potential…. None were rated high or critical severity.
Is MiroFish safe?
ClawSecure audited MiroFish and assigned a security score of 80/100 (Safe), identifying 4 findings across ReDoS and Permissions Manifest. Review the findings below before installing.
What did ClawSecure find in MiroFish?
ClawSecure identified 4 findings in MiroFish, concentrated in ReDoS and Permissions Manifest. The most severe include Missing config.json - agent may not be properly configured and ReDoS vulnerability: Nested quantifiers (potential….
How was MiroFish audited?
ClawSecure ran MiroFish through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 69 files from 666ghj/MiroFish.
What does a score of 80 mean?
ClawSecure assigned MiroFish a security score of 80/100, placing it in the Safe range. Scores of 80 or above qualify for ClawSecure Verified status; the 4 findings detected are lower-severity. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).
Audit Findings for MiroFish
ClawSecure detected 4 security findings in MiroFish, spanning ReDoS and Permissions Manifest.
- medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- medium · ReDoS vulnerability: Nested quantifiers (potential…. ReDoS finding detected in
oasis_profile_generator.py:673. - medium · ReDoS vulnerability: Nested quantifiers (potential…. ReDoS finding detected in
simulation_config_generator.py:522. - medium · ReDoS vulnerability: Nested quantifiers (potential…. ReDoS finding detected in
zep_tools.py:1498.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for MiroFish
Fix ReDoS-prone patterns
Add a config.json permissions manifest
Pin dependencies to exact versions
1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. ClawSecure checks every dependency against known CVE databases.Related Security Research
Why Generic Scanners Fail at AI Agent Security→Understanding Our 3-Layer Audit Protocol→How to Secure an MCP Server: The 2026 Guide→Related AI Agent Security Audits
Scanned on July 22, 2026. MiroFish is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.