manipulation-detector
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: manipulation-detector Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'manipulation-detector' is benign. The Python script `scripts/detect.py` performs text analysis using regular expressions to identify manipulation patterns, reading input from stdin or a user-specified file and printing results to stdout. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts in `SKILL.md` or `README.md`. All code and documentation align with the stated purpose of helping agents calibrate skepticism by detecting common influence tactics.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Users need Python available for the examples to work.
The skill's usage depends on python3, while the registry requirements declare no required binaries. This is a metadata completeness gap, but the dependency is expected for the included script and does not indicate hidden behavior.
echo "Your text here" | python3 scripts/detect.py
Declare python3 as a required binary in the skill metadata, or make clear that it is an expected local prerequisite.