CC tsa-compliance
Expert TSA cybersecurity compliance advisor for critical infrastructure owners and operators. Use this skill whenever a user asks about TSA Security Directives for pipelines, freight railroads, passenger rail, public transit, or bus operators; the TSA Cyber Risk Management Program (CRMP); Cybersecurity Implementation Plan (CIP); Cybersecurity Operational Implementation Plan (COIP); Cybersecurity Assessment Plan (CAP); incident reporting to CISA; designation of a Cybersecurity Coordinator; Critical Cyber Systems (CCS); OT/IT network segmentation; the TSA November 2024 NPRM; or any directive in the SD Pipeline-2021 series, SD 1580-21-01 (freight rail), or SD 1582-21-01 (public transit/passenger rail). Also trigger for questions like "are we covered by TSA directives?", "what does the TSA require for pipeline cybersecurity?", "how do I build a CIP?", "what must I report to CISA?", or any request involving transportation critical infrastructure cybersecurity compliance.
Expert TSA cybersecurity compliance advisor for critical infrastructure owners and operators.
As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
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 · 14
✓ No critical or high findings
Medium and low: 14
-
low Risky intent
intent-offensive-securityREADME.md:39Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; documentation table row)| **Incident reporting** | "We've detected ransomware on our IT network. It hasn't reached our SCADA yet. Do we need to report to CISA?" |
detectortable -
low Risky intent
intent-offensive-securityreferences/tsa-crmp-requirements.md:143Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. **Ransomware response drill**: Malware detected on IT; test containment, backup integrity check, restoration procedure
-
low Risky intent
intent-offensive-securityreferences/tsa-crmp-requirements.md:233Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Penetration testing | Authorised simulated attack to test defences | IT; OT where safe and agreed |
-
low Risky intent
intent-offensive-securityreferences/tsa-crmp-requirements.md:236Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Red team exercise | Adversary simulation against CCS | Large/complex environments |
-
low Risky intent
intent-offensive-securityreferences/tsa-crmp-requirements.md:240Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Penetration testing in OT requires vendor coordination and operational approval
-
low Risky intent
intent-offensive-securityreferences/tsa-crmp-requirements.md:249Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Q3 | Penetration test (IT external + internal) | IT CCS |
-
low Risky intent
intent-offensive-securityreferences/tsa-directives-overview.md:12Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Following the May 2021 Colonial Pipeline ransomware attack, TSA issued mandatory cybersecurity Security Directives requiring critical transportation infrastructure owners and operators to implement ba
-
low Risky intent
intent-offensive-securityreferences/tsa-incident-reporting.md:20Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Ransomware infection confirmed on IT or OT systems
-
low Risky intent
intent-offensive-securityreferences/tsa-incident-reporting.md:34Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Evidence of lateral movement in IT with potential path to OT
-
low Risky intent
intent-offensive-securityreferences/tsa-incident-reporting.md:85Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)> "[Organisation Name], a [natural gas pipeline / freight railroad / transit agency] operator, is reporting a cybersecurity incident identified on [date/time]. We detected [ransomware/unauthorised acc
detector -
low Risky intent
intent-offensive-securitySKILL.md:108Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Discovery of malware or ransomware on CCS
-
low Risky intent
intent-offensive-securitySKILL.md:168Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Verifying containment procedures for a simulated ransomware event
-
low Risky intent
intent-offensive-securitySKILL.md:191Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Assessment methodology: penetration testing, vulnerability scanning, configuration review, process review
-
low Risky intent
intent-offensive-securitySKILL.md:252Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- Focus on detecting: lateral movement, unusual protocol use, unauthorised devices, credential abuse
detector
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5188 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 257, 264): 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
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (tsa-compliance) differs from the folder (tsa-compliance-tanaji-hemant-naik)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5188 tokens
- 85Steps. 114 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Progress reporting. Reports progress
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 980: 120–800 characters recommended
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 35 headings
- +3Step-by-step instructions: 114 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.