BC dcl-provenance-tracker
Verify the integrity and version history of any ClawHub skill after an update. Compares two versions of a skill side-by-side, detects suspicious drift across 30+ known supply chain attack patterns, and returns a deterministic DCL provenance proof. 100% instruction-only for the diff itself — no external calls, no data leaves the agent. Optionally cross-check a past scan's on-chain integrity via the live DCL Trust Oracle MCP server. Use after every skill update, on a schedule for production-critical skills, or in CI/CD pipelines before agent deployment. Part of the DCL Skills security suite by Fronesis Labs alongside DCL Skill Auditor, DCL Policy Enforcer, DCL Sentinel Trace, and DCL Semantic Drift Guard.
As a process C 63/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 10
✓ No critical or high findings
Medium and low: 10
-
low Risky intent
intent-offensive-securitySKILL.md:44Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Reverse shell or pipe-to-shell patterns
-
low Risky intent
intent-offensive-securitySKILL.md:153Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [ ] New reverse shell: `/dev/tcp/`, `nc -e`, `bash -i >&`
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:222High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"dcl_fingerprint": "DCL-…a0e"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:251High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"dcl_fingerprint": "DCL-…c05"
detector
A further 6 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 63/100
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 60 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2840 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 712: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 60 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.