Skills/npm/offsec-exploit-research

offsec-exploit-research@1.0.3

CAUTION

Publisher claims: "Elite adaptive whitebox exploit research skill for Claude Code and OpenCode. Classifies targets, loads domain-specific methodology, and hunts real vulnerabilities." Observed in sandbox: static analysis only — behavior not yet observed.

Registry npm (MCP server)Publisher offsec-skills · joined 6 days agoInstalls 41Last detonated 6d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-28 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Authorization escalation language; Authorization escalation language; Prompt injection. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Authorization escalation languageskill/SKILL.md:317 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageskill/SKILL.md:183 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionskill/references/sandbox-boundaries.md:58 · Prompt injection — explicit attempt to bypass safety measuresFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Authorization escalation languageskill/SKILL.md:276 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim offsec-skills: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim offsec-skills