BC antenna
Session-targeted, cross-host, agent-native messaging. Your agents, their agents, any host, any session.
Session-targeted, cross-host, agent-native messaging.
As a process C 58/100 · Has gaps — weak spots: result and completion, execution cost, 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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Obfuscation
obf-base64-blobreferences/ED25519-PROTOCOL-V1.md:142Long base64-looking blobn1d1…pDQ==
-
low Exfiltration
net-credential-usescripts/antenna-exchange.sh:1375Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)interactive_account="$(confirm_from_account "$default_acct" "$interactive_email" "$pubkey_subject" || true)"
quoted
Files scanned: 56. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9148 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 53, 57, 86, 96, 107, 373): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 42 mutating operations with no state check
- 40Execution cost. Instruction body is 9148 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 117 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 tags): a typed call is more reliable
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)
- +3Description length 103: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -319 of 21 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 26 headings
- +3Step-by-step instructions: 117 items
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.