CC zoho-email-integration
Complete Zoho Mail integration with OAuth2, REST API (5-10x faster), Clawdbot /email commands, HTML emails, attachments, and batch operations. Security-hardened against path traversal and command injection. Perfect for email automation and workflows.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
-
low Risky intent
intent-offensive-securityCHANGELOG.md:52Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **CRITICAL: Path traversal in attachment download** - The `download_attachment()` function in `scripts/zoho-email.py` used untrusted email attachment filenames directly for file writes. An attacker
detector -
low Risky intent
intent-offensive-securityCHANGELOG.md:71Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Path traversal** → Remote code execution, privilege escalation, data exfiltration
-
low Risky intent
intent-offensive-securitySECURITY.md:71Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Impact:** Prevents arbitrary file write, remote code execution, and privilege escalation through malicious email attachments.
A further 6 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 32. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 30 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4495 tokens
- 100Steps. 74 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 17 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
- -236 emoji in the instructions: noise for the model
- -35 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 250: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (41 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.