SkillSpector · academic-pipeline

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

agents/collaboration_depth_agent.md

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

agents/pipeline_orchestrator_agent.md

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

agents/pipeline_orchestrator_agent.md

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

references/passport_as_reset_boundary.md

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

agents/claim_ref_alignment_audit_agent.md

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

agents/claim_ref_alignment_audit_agent.md

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

agents/claim_ref_alignment_audit_agent.md

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

agents/pipeline_orchestrator_agent.md

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

agents/pipeline_orchestrator_agent.md

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

agents/state_tracker_agent.md