Agent skill for release-manager - invoke with $agent-release-manager
49
28%
Does it follow best practices?
Impact
78%
2.51xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/agent-release-manager/SKILL.mdLow
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Potentially malicious external URL detected (high risk: 0.80). The skill runs npx commands (e.g., "npx ruv-swarm hook ..." which will fetch/execute the ruv-swarm package from the npm registry, effectively https://registry.npmjs.org/ruv-swarm) and performs runtime git/gh operations (e.g., "gh repo clone :owner/:repo" -> https://github.com/:owner/:repo.git) that fetch remote code which is executed as part of the hooks/pipeline, so these external fetches directly execute remote code and are required for the skill to run.
26c35b5
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.