Security audit
Security checks for vulnerabilities and agentic risk
Logic Hunter is a straightforward fact-checking and evidence-scoring skill; its external search use is expected for that purpose, though users should avoid submitting sensitive claims to search tools.
Install only if you want research requests handled with evidence grading and red-team style critique. Treat searched claims as potentially shared with external search providers, and avoid using it for confidential, personal, or proprietary topics unless your environment's search tooling is approved for that data.
The README says users can trigger the skill by 'describing what you need' and gives examples like 'Analyze the credibility of [statement]'. These are common phrasings that could match everyday conversation, and the file does not define narrower trigger constraints or exclusion conditions for when the skill should not activate.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
Copy the skill files to your Claude Code skills directory:
# Create the skill directory
mkdir -p ~/.claude/skills/logic-hunter
# Copy the files
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
# Create the skill directory
mkdir -p ~/.claude/skills/logic-hunter
# Copy the files
cp SKILL.md ~/.claude/skills/logic-hunter/
The skill instructs the agent to call external search tools but does not warn that user queries may be transmitted to third-party services. This creates a privacy and data-governance risk, especially if users submit sensitive claims, internal topics, or proprietary research questions that are then sent off-platform without informed consent.
The trigger conditions are broad enough to activate on ordinary research and verification requests, which can cause the skill to intercept general-purpose queries unexpectedly. In this skill, that matters because activation leads to external search and analysis steps, increasing the chance of unnecessary data disclosure and unintended tool use.
This code file contains natural-language strings and docstrings primarily in Chinese, including the module description and class description, while also exposing a CLI intended for direct user interaction. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the restriction is explicitly justified or optionality is offered.
The description includes Chinese text ('证据溯源') embedded in otherwise English instructions, which introduces a language/locale inconsistency without explaining whether the skill targets bilingual users or offering language selection. Under the policy, language behavior should be opt-in or clearly justified when constrained.
No suspicious patterns detected.