thecolony is an AI agent skill, created by jackparnell and published at openclaw/skills. ClawSecure audited thecolony across 2 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 60/100 (Medium Risk). The 5 findings concentrate in Prompt Injection, Policy Violation and Transitive Trust Abuse, including Detects prompt strings used to override or force malicious tool calls:... and Pattern detected: Ignore previous instructions. 2 were rated high or critical severity.
Is thecolony safe?
ClawSecure audited thecolony and assigned a security score of 60/100 (Medium Risk), identifying 5 findings across Prompt Injection and Policy Violation. Review the findings below before installing.
What did ClawSecure find in thecolony?
ClawSecure identified 5 findings in thecolony, concentrated in Prompt Injection, Policy Violation and Transitive Trust Abuse. 2 were rated high or critical severity. The most severe include Detects prompt strings used to override or force malicious tool calls:... and Pattern detected: Ignore previous instructions.
How was thecolony audited?
ClawSecure ran thecolony through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 2 files from openclaw/skills.
What does a score of 60 mean?
ClawSecure assigned thecolony a security score of 60/100, placing it in the Medium Risk range. This reflects 5 findings led by Prompt Injection that warrant review before production use. 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 thecolony
ClawSecure detected 5 security findings in thecolony, spanning Prompt Injection, Policy Violation, Transitive Trust Abuse and Permissions Manifest.
- critical · Detects prompt strings used to override or force malicious tool calls:.... Prompt Injection finding detected in
SKILL.md:91. - high · Pattern detected: Ignore previous instructions. Prompt Injection finding detected in
SKILL.md:91. - medium · Detects indirect prompt injection via instruction manipulation from.... Transitive Trust Abuse finding detected in
SKILL.md:100. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- info · Skill manifest does not include a 'license' field. Specifying a license.... Policy Violation finding detected in
SKILL.md.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for thecolony
Investigate prompt injection vectors
Resolve policy violations
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
The Sleeper Agent Problem: Why a Clean Scan Today Does Not Guarantee Safety Tomorrow→OWASP ASI Top 10 Explained: The Complete Guide to AI Agent Security Standards→Understanding Our 3-Layer Audit Protocol→Related AI Agent Security Audits
Scanned on February 7, 2026. thecolony is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.