honeypot-trap-guard
Skill4 starsChanged 31 days agoMITView on GitHub
Detect automated AI slop and ungrounded LLM ingestion using active prompt canary traps, decoy issue references, and decoy template checkboxes while preventing self-blocking on template maintenance.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- anti-slop-engineeringSkill
- anti-slop-engineeringSkill
- api-ergonomics-and-contract-governorSkill
- apple-craft-and-frame-budgetSkill
- apple-craft-and-interaction-physicsSkill
- asset-provenance-guardSkill
- backprop-guardSkill
- chaos-and-degradation-choreographerSkill
- chromatic-drift-guardSkill
- cognitive-load-and-attention-governorSkill
- comment-budget-guardSkill
- context-window-and-token-economics-architectSkill
- cryptographic-agility-and-secret-lifecycle-gateSkill
- decision-guardSkill
- demock-guardSkill
- design-system-drift-guardSkill
- deterministic-simulation-and-property-testingSkill
- distributed-consensus-and-concurrency-gateSkill
- finops-and-unit-economics-governorSkill
- future-scale-gateSkill
- grumpy-senior-staff-engineerSkill
- house-tell-guardSkill
- install-anti-slopSkill
- llm-eval-and-prompt-injection-fortressSkill
- mandela-guardSkill
- mechanical-sympathy-and-perf-gateSkill
- mechanical-sympathy-profilerSkill
- motion-runtime-guardSkill
- observability-and-slo-architectSkill
- observability-and-slo-gateSkill
- paranoid-principal-architectSkill
- pr-boundary-guardSkill
- privacy-and-data-lineage-gateSkill
- re0-handoff-guardSkill
- reduction-guardSkill
- repo-memory-and-invariant-stewardSkill
- root-fix-gateSkill
- safe-evolution-and-rollout-choreographerSkill
- scientific-fault-isolationSkill
- styleseed-guardSkill
- supply-chain-and-sbom-sentinelSkill
- tagore-guardSkill
- type-level-and-ast-slop-gateSkill
- ui-and-copy-disciplineSkill
- verification-oracle-architectSkill
- zero-downtime-migration-gateSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Active trap over passive substring: Never flag standard HTML comments that GitHub automatically populates into the PR text box.
- Very specific: line 27
Template maintenance isolation: Never evaluate honeypot traps against diffs in .github/ templates or workflow files.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Honeypot Trap & Prompt Canary Guard
Catch automated bot campaigns and ungrounded AI ingestion using active canary tokens, decoy issues, and decoy checkbox traps with zero false positives.
Why This Skill Is Needed & Target State
Automated AI agents frequently scrape issues, PR templates, and issue trackers, echoing instructions, hallucinating fixes, or submitting mass PRs without human review. Passive regex filters can false-positive on human contributors or get evaded by clever prompt wrappers.
The target state is an active canary trap defense:
- Canary tokens: Deterministic HMAC-SHA256 tokens embedded as invisible HTML instructions in issue templates (
<!-- anti-slop-canary:canary-xxx -->). If an automated agent echoes or acknowledges the canary, it is flagged with 100% precision. - Decoy issue numbers: Known non-existent issue numbers (
#9999,#8888) placed in bait questions. Automated bots referencing them are trapped. - Decoy checkboxes: Obvious bait checkboxes (e.g.
- [ ] I confirm this PR contains quantum teleportation) that humans naturally leave unchecked, but ungrounded LLM summarizers blindly check. - Maintenance exemption: Edits to
.github/templates and workflow files are strictly exempt so maintainers are never self-blocked.
Invariant Rules
- Active trap over passive substring: Never flag standard HTML comments that GitHub automatically populates into the PR text box. Only flag when an active instruction is explicitly triggered.
- Template maintenance isolation: Never evaluate honeypot traps against diffs in
.github/templates or workflow files. - Deterministic verification: Canary tokens must be generated deterministically via HMAC-SHA256 to allow verifiable rotation without persistent databases.
CLI Usage
# Generate a new HMAC canary token to place in issue/PR templates
bunx anti-slop-engineering honeypot --generate-canary --secret "my-repo-secret"
# Audit a PR description or git diff against active canary tokens
bunx anti-slop-engineering honeypot \
--pr-body-file pr_body.md \
--canary-token canary-98fbc12a \
--diff-file diff.patch \
--jsonDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

