Skill/Static safety grade

productclank-agent-participation

github/covariance-network/productclank-agent-skill#productclank-agent-participation

litmus-skill-v1 · 2026-06-23

graded at commit 158ac3d · 2026-06-18

The productclank-agent-participation skill is graded A by polygraph under litmus-skill-v1, as of 2026-06-23, anchored to its content hash.

Graded under litmus-skill-v1; the current skill methodology is litmus-skill-v2. A re-run may change the grade.

Self-reported “Earn by participating in ProductClank Communiply campaigns. Your agent discovers AI-generated reply drafts for live campaigns, posts them from its OWN X (Twitter) account, submits the tweet URL, and earns leaderboard points, platform credits, and $PRO. Use when an agent should…” — the skill’s own SKILL.md description at the graded commit, not part of the grade.

A static safety grade — a deterministic scan of the skill’s SKILL.md and bundled files. An A means static-clean, not behavioral proof: a skill’s instructions are interpreted by an agent at runtime.

Share on X

S-01 Prompt-injection / context-poisoningpass

S-03 Data-exfiltration instructionspass

S-04 Dangerous bundled commandspass

content hash · 0xd4e7c35d68…9f9a

Source · github.com/covariance-network/productclank-agent-skill/tree/main/productclank-agent-participation

Watch for changes

This grade is a snapshot of the skill’s files at one commit. Get an email when a new commit changes productclank-agent-participation and polygraph re-runs the litmus — one message per change, one-click unsubscribe.

Monitor this skill

Reproduce this grade

The skill litmus is open and deterministic. Point it at the skill directory and compare the grade and content hash — a false grade is falsifiable, not merely disputable.

npx -p @polygraphso/litmus polygraphso-litmus-skill <skill-dir>

Embed this badge

Drop it in the skill’s README, docs, or listing. It always shows the current grade and links back here.

Markdown — badge

[![polygraph](https://www.polygraph.so/api/badge/skill?skill=github/covariance-network/productclank-agent-skill/productclank-agent-participation)](https://www.polygraph.so/skill/github/covariance-network/productclank-agent-skill/productclank-agent-participation)

HTML — badge

<a href="https://www.polygraph.so/skill/github/covariance-network/productclank-agent-skill/productclank-agent-participation"><img src="https://www.polygraph.so/api/badge/skill?skill=github/covariance-network/productclank-agent-skill/productclank-agent-participation" alt="polygraph grade"></a>

Markdown — card

[![polygraph](https://www.polygraph.so/api/badge/skill/card?skill=github/covariance-network/productclank-agent-skill/productclank-agent-participation)](https://www.polygraph.so/skill/github/covariance-network/productclank-agent-skill/productclank-agent-participation)

Questions

What does the A skill grade mean for productclank-agent-participation?: It’s a static safety grade(A/B/D/F) from a deterministic scan of the skill’s SKILL.md and bundled files. An A means static-clean — not behavioral proof, since a skill’s instructions are interpreted by an agent at runtime.
What did polygraph check?: Three static checks: S-01 prompt-injection and context-poisoning, S-03 data-exfiltration instructions, and S-04 dangerous bundled commands. The full battery is in the methodology.
How do I reproduce this grade?: Run npx -p @polygraphso/litmus polygraphso-litmus-skill <skill-dir>. The scan is open and deterministic, anchored to the skill’s content hash, so the same directory yields the same grade.