BC unipile-linkedin
Interact with LinkedIn via Unipile API - send messages, view profiles, manage connections, create posts, react to content. Use when the user asks to message someone on LinkedIn, check LinkedIn messages, view LinkedIn profiles, send connection requests, create LinkedIn posts, or interact with LinkedIn content.
Interact with LinkedIn via Unipile API - send messages, view profiles, manage connections, create posts, react to content.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 · 11
✓ No critical or high findings
Medium and low: 11
-
medium Concealment
en-hide-from-userresources/last_50_posts.json:188Instruction to hide actions from the user (quoted — discussed, not commanded)"text": "New research from Meta Superintelligence Labs challenges how we route models for complex tasks.\n\nThe work introduces a strategy-auction framework for improving self-optimizing agents, and i
quoted -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:18High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha512-/s55Jujywdw/Jpan+vsy6…4pq+uOt7…4aQ==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:195High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…9ZZ/0wAx…8jy/kbhs…gJ5+F2mt…V7I+EoRK…K7A==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:225High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…2YE+3fQp…lVw==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:260High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…4hd+2E8N…oYe/ZdlJy+J3uC…Hmg==",
detector -
low Secrets in code
secret-high-entropy-tokenresources/last_50_posts.json:36High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"id": "ACoA…_PI",
quoted -
low Secrets in code
secret-high-entropy-tokenresources/last_50_posts.json:66High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"id": "ACoA…_PI",
quoted -
low Secrets in code
secret-high-entropy-tokenresources/last_50_posts.json:83High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"id": "ACoA…gD4",
quoted -
low Secrets in code
secret-high-entropy-tokenresources/last_50_posts.json:121High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"id": "ACoA…_PI",
quoted -
low Secrets in code
secret-high-entropy-tokenresources/last_50_posts.json:163High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"id": "ACoA…_PI",
quoted -
low Obfuscation
obf-base64-blobresources/last_50_posts.json:2112Long base64-looking blob (quoted — discussed, not commanded)"cursor": "eyJw…TB9",
quoted
Files scanned: 6. 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 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 899 tokens
- 100Running it twice. No mutating operations
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
- +1No license
- +2Single-language instructions
- +3Description length 310: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (8 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.