social-writer
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: social-writer Version: 1.0.0 The OpenClaw AgentSkills bundle 'social-writer' is benign. All files (`_meta.json`, `SKILL.md`, `prompt.txt`) consistently define a skill for generating social media content with a specific, opinionated style. The instructions in `SKILL.md` and `prompt.txt` are solely focused on guiding the LLM's output format and tone, without any directives for the agent to perform unauthorized actions, access sensitive data, or execute commands. There is no evidence of prompt injection against the agent, data exfiltration, malicious execution, or other harmful behaviors.
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.
Generated posts could sound like the user personally experienced or believes something, so publishing without review may affect reputation or accuracy.
The skill intentionally generates first-person, opinionated social copy. This is aligned with the copywriting purpose, but it may imply personal experience or strong views that the user did not actually provide.
Use "I" and "you"... share war stories, don't be afraid to ruffle feathers.
Review and edit generated posts to ensure any first-person claims, opinions, or anecdotes are truthful and appropriate before publishing.