github-project-triage
What this skill does
GitHub project triage tool for analyzing issues, PRs, and activity in repositories
github/steipete - Command Injection - 6.5k stars
Threat analysis
Skill info
pkg:github/steipete/agent-scripts@bce6015?skill=github-project-triageAssessments (2)
Command Injection
Command Injection via local-llm-review
scripts/github-activity.sh
The script uses untrusted input in several API calls and command-line arguments without proper sanitization. For example, the `repo` variable is set to `openclaw/openclaw` but could be modified by useInformation Exposure
Information Exposure via local-llm-review
scripts/github-activity.sh
The script includes functions like `rough_age` that expose the age of repositories and user activity, which could be used to infer sensitive information about the user's GitHub activity and history.Badge
Add the Anomity scan badge for github-project-triage 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 github-project-triage? Report an issue or request a rescan.
