AC google-services-secure
Secure Google Workspace integration (Gmail, Drive, Calendar, Sheets, Docs, Contacts, etc.) with enterprise-grade security. Features credential isolation, input validation, audit logging, rate limiting, and granular permissions. Use when working with Google APIs, sending emails, managing files, scheduling calendar events, or automating Google Workspace workflows.
As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Exfiltration
net-credential-useCHANGELOG.md:145Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -H "Authorization: Bearer $ACCESS_TOKEN" \
security skill -
low Exfiltration
net-credential-useCONTRIBUTING.md:84Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -H "Authorization: Bearer $ACCESS_TOKEN" \
security skill -
low Exfiltration
net-credential-useCONTRIBUTING.md:242Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -H "Authorization: Bearer $ACCESS_TOKEN" \
security skill -
low Risky intent
intent-offensive-securityreferences/security.md:232Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Periodic penetration testing
-
low Dangerous commands
cmd-shell-rcreferences/security.md:298Writes to a shell startup file (documentation of a security skill)echo 'export GOOGLE_CLIENT_SECRET="..."' >> ~/.bashrc # ⚠️ INSECURE
security skill -
low Risky intent
intent-offensive-securityreferences/security.md:389Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Potential bug bounty (if program exists)
Files scanned: 10. 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 64/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4054 tokens
- 100Tools and files. No external tools needed
- 100Steps. 73 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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
- -2localhost URLs: will not work for another user
- -242 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 364: enough signal without eating the budget
- +4Structure: 61 headings
- +3Step-by-step instructions: 73 items
- +4Has examples (44 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.