BB ocas-multipass
Accomplishes tasks that need tools the agent does not have. Plans approaches, fills capability gaps with sandboxed tools, executes within an isolated session. Disposable identity, parallel discovery, incremental checkpoints, graceful degradation. Output: task result plus replay script. No global installs, no real identity, clean state in and out. Do not use for tasks solvable with installed skills, permanent skill installs, skill builds (use Forge), or general web research (use Sift).
Accomplishes tasks that need tools the agent does not have.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
exfil-send-secrets-to-urlreferences/resilience.md:110Instruction to send secrets/history to an external endpoint (describes API authentication (bearer / header / HTTPS); documentation table row; documentation of a security skill)| 2 | Mail.tm | days | `POST https://api.mail.tm/accounts` (get domains: `GET https://api.mail.tm/domains`) | `POST https://api.mail.tm/token` then `GET https://api.mail.tm/messages` with Bearer token
API authtablesecurity skill
Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "includes" - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2056 tokens
- 100Progress reporting. Reports progress
- low 20 top-level sections: this looks like several domains in one skill
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 489: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 44 items
- +4Reference files are cited in the instructions (11 of 11)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.