BC otc-confirmation
One-Time Confirmation code security mechanism for sensitive agent operations. Generates a cryptographically secure single-use code, delivers it via a private channel (email), and requires the user to reply with the code before execution proceeds. The code never appears in stdout, logs, or chat — it flows through a secure state file. Use when the agent needs to confirm dangerous, irreversible, or externally-visible operations.
As a process C 55/100 · Has gaps — 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.
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 · 14
✓ No critical or high findings
Medium and low: 14
-
medium Exfiltration
exfil-read-secret-filesai-devops-agent-security-pack/code_examples/permission_guard.py:304Reads credential / secret files (documentation of a security skill)("developer", Operation(type="file_read", path="~/.ssh/id_rsa")),security skill -
low Risky intent
intent-offensive-securityai-devops-agent-security-pack/01_agent_security_architecture.md:36Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**4. Privilege Escalation Through Chaining**
-
low Risky intent
intent-offensive-securityai-devops-agent-security-pack/06_risk_detection.md:117Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)"description": "Potential reverse shell"
quoted -
low Risky intent
intent-offensive-securityai-devops-agent-security-pack/06_risk_detection.md:178Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)# Pattern: Privilege escalation attempt
detector -
low Risky intent
intent-offensive-securityai-devops-agent-security-pack/06_risk_detection.md:181Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)alerts.append("PRIVESC: Potential privilege escalation sequence")detector
A further 9 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 29. 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 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 18 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 30 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1918 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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 429: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.