BC researchers-security
Researches malware analysis, CVEs, attribution reports, and hacker community sources. Use when the album subject involves cybersecurity incidents or threat actors.
Researches malware analysis, CVEs, attribution reports, and hacker community sources.
As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
For the model run — optional
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
low Risky intent
intent-offensive-securityCVE_RESEARCH.md:89Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| CrowdStrike | crowdstrike.com/blog | Nation-state, ransomware |
-
low Risky intent
intent-offensive-securityCVE_RESEARCH.md:90Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Kaspersky | securelist.com | Malware analysis |
-
low Risky intent
intent-offensive-securityCVE_RESEARCH.md:102Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Malware Analysis Resources
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Researches malware analysis, CVEs, attribution reports, and hacker community sources. Use when the album subject involves cybersecurity incidents or threat actors.
-
low Risky intent
intent-offensive-securitySKILL.md:33Offensive-security / dual-use content (legitimate for authorised testing; review intended use)You are a cybersecurity specialist for documentary music projects. You research malware analysis, hacking incidents, threat intelligence, and security community sources.
-
low Risky intent
intent-offensive-securitySKILL.md:44Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Malware analysis reports
-
low Risky intent
intent-offensive-securitySKILL.md:116Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Detailed malware analysis
-
low Risky intent
intent-offensive-securitySKILL.md:251Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **C2/C&C** | Command and control | "C2 server calling home" |
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "effort"
Process rating: all ten parameters 57/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 97 steps, 2 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2161 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +3Description length 163: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 97 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.