comet-classic-039-verify
What this skill does
Verification and closing phase of a Comet workflow. It checks if implementation matches design, handles development branches, and performs scale assessments.
github/rpamis - Command Injection - 2.7k stars
Threat analysis
Skill info
pkg:github/rpamis/comet@b8f6334?skill=comet-classic-039-verifyAssessments (2)
Command Injection
Command Injection via local-llm-review
SKILL.md
The script uses untrusted input `<change-name>` directly in a command without validation or sanitization. This could allow an attacker to inject arbitrary shell commands.Path Traversal
Path Traversal via local-llm-review
SKILL.md
The script uses `find` with untrusted input in the path expression. This could allow an attacker to traverse directories and access files outside the intended scope.Badge
Add the Anomity scan badge for comet-classic-039-verify to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of comet-classic-039-verify? Report an issue or request a rescan.
