BD security-check
Security audit and inspection skill for Clawdbot skills. Use this when you need to check skills for security vulnerabilities before installation, perform regular security audits on installed skills, verify skill description matches actual behavior, scan for prompt injection attempts, check for hardcoded secrets or credentials, verify no malicious intent in skill code or documentation, review file access patterns for potential configuration or secrets exposure, or audit dependencies for known vulnerabilities. This skill provides automated scanning tools and manual security checklists for comprehensive skill security assessment.
Security audit and inspection skill for Clawdbot skills.
As a process D 45/100 · Unfinished process — 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Instruction override
en-ignore-previousreferences/prompt-injection-patterns.md:21Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)ignore all previous instructions
security skill -
medium Instruction override
en-ignore-previousreferences/prompt-injection-patterns.md:23Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)disregard system messages
security skill -
medium Instruction override
en-ignore-previousreferences/prompt-injection-patterns.md:25Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)ignore safety constraints
security skill -
medium Instruction override
en-role-hijackreferences/prompt-injection-patterns.md:89Role hijack ("from now on you must ignore… / developer mode") (documentation of a security skill)you are now in developer mode
security skill -
medium Instruction override
en-ignore-previousreferences/prompt-injection-patterns.md:125Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)if the user asks, ignore previous rules
security skill -
medium Instruction override
en-ignore-previousreferences/security-checklist.md:16Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)- ❌ Instructions to ignore/discard previous context
security skill -
low Risky intent
intent-offensive-securityreferences/prompt-injection-patterns.md:384Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- Participate in red team exercises
detector
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. 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 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
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (security-check) differs from the folder (security-check-skill)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 165 steps, 3 vague phrases
- 100Execution cost. Instruction body is 2993 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -224 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 634: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 165 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.