qa-team
What this skill does
Multi-agent code review tool that spawns parallel specialist agents to review code changes and produce a converged report.
github/posthog - Code Injection - 37.6k stars
Threat analysis
Skill info
pkg:github/PostHog/posthog@d885c87?skill=qa-teamAssessments (2)
Code Injection
Code Injection via local-llm-review
scripts/build_launch_scripts.js
The PROMPT_TEMPLATE includes a Bash command that executes '__RUN_DIR__/claim_persona.sh', which could be exploited if the RUN_DIR is not properly sanitized or controlled by the user.Path Traversal
Path Traversal via local-llm-review
scripts/claim_persona.sh
The script uses '$dir' without proper validation, which could allow an attacker to manipulate the directory path and access files outside the intended scope.Badge
Add the Anomity scan badge for qa-team 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 qa-team? Report an issue or request a rescan.
