BC ccs-receipt-batch-audit
Batch Ed25519 signature verification for up to 200 AI-agent audit receipts, fully offline. Every receipt is checked against one issuer public key with Ed25519 verification plus RFC 8785 JCS/SHA-256 integrity checks; outputs aggregate valid/invalid statistics, pass rate, tampered-index list with per-receipt failure reasons, and optional hash-chain linkage, using the vendored open-source CCS verification core. Zero network calls. Use when batch-verifying CCS receipts, auditing a batch of signed agent decision receipts, or verifying a receipt chain.
Batch Ed25519 signature verification for up to 200 AI-agent audit receipts, fully offline.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Exfiltration
net-redirectable-api-keyscripts/ccs_online_client.py:58Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Secrets in code
secret-high-entropy-tokenexamples/batch_mixed.json:2High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)"public_key_pem": "-----BEGIN PUBLIC KEY-----\nMCo…X3M+KzBa…8k8=\n-----END PUBLIC KEY-----\n",
fixturequoted -
low Obfuscation
obf-base64-blobexamples/batch_mixed.json:71Long base64-looking blob (detector / deny-list definition; test fixture / example file)"signature": "0XlC…z4p/CwkJ…Kff/ZDdu…LZx+x4ML8Aw=="
detectorfixture -
low Obfuscation
obf-base64-blobexamples/batch_mixed.json:139Long base64-looking blob (detector / deny-list definition; test fixture / example file)"signature": "KhoY…Zcg+lE319PRwLP/l0Iq…XLI+xzRJ…6z6+eyDA=="
detectorfixture -
low Obfuscation
obf-base64-blobexamples/batch_mixed.json:207Long base64-looking blob (detector / deny-list definition; test fixture / example file)"signature": "XCoY…xmf+4MdO…Ids/2JdJfhG2+upWBKbAZvwBRvAzqwwTtSalkDPupmpDQ=="
detectorfixture -
low Obfuscation
obf-base64-blobexamples/batch_mixed.json:275Long base64-looking blob (detector / deny-list definition; test fixture / example file)"signature": "jLsU…IOb/6Ozk…5vc+2vkU…lAQ=="
detectorfixture -
low Obfuscation
obf-base64-blobexamples/batch_mixed.json:343Long base64-looking blob (detector / deny-list definition; test fixture / example file)"signature": "lHHR…Z9B/2VxT…xqt/dRFip9p/Q0Ah…zDw=="
detectorfixture
Files scanned: 9. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1412 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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)
- +3Output format is not stated: the model decides each time
- -35 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 552: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.