BD RedactKit - AI Privacy Scrubber
Scan your data before sending it to AI. Detect and redact PII, secrets, and sensitive info. Reversible, local, zero network calls.
As a process D 39/100 · 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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Secrets in code
secret-private-keyLIMITATIONS.md:146Private key material (detector / deny-list definition; key header without key body)**Workaround:** Patterns include PEM header detection (`-----BEGIN PRIVATE KEY----- …
detectorheader only -
low Secrets in code
secret-labelled-tokenREADME.md:238Labelled token / key literal (vendor format unknown — verify it is not a live credential) (placeholder value)# "Contact su…@….com for help. API key: EXAM…123"
placeholder -
low Risky intent
intent-offensive-securityREADME.md:407Offensive-security / dual-use content (legitimate for authorised testing; review intended use)is NOT a replacement for professional security auditing, penetration testing, or
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 39/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (RedactKit - AI Privacy Scrubber) differs from the folder (redact-kit)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 8 steps
- 100Execution cost. Instruction body is 791 tokens
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
- +2Single-language instructions
- +3Description length 130: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.