Verdict safe, but 2 findings (2 medium), mainly data exfiltration, unauthorized tool use. Most recent scan 2026-02-06.
This email management skill presents MEDIUM security risk due to missing implementation code and incomplete packaging. The skill claims to perform highly sensitive operations (send/read emails, access credentials for Gmail/Outlook/IMAP) but provides no visible code for security review. The referenced 'last.py' file is missing, creating a critical gap in verifying the skill's actual behavior. The 'always: True' flag combined with missing implementation raises concerns about potential unauthorized access or tool shadowing. While no active malicious code was detected (because no code is present), the combination of high-risk operations, missing implementation, external binary dependencies (curl/jq), and incomplete packaging creates significant security uncertainty. The skill cannot be verified as safe without the complete implementation.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Email management and automation. Send, read, search, and organize emails across multiple providers.
- Package
- 1 file, 563 B
- SKILL.md
- 54 words, 4 sections
- Code
- None. Instructions only.
- Requires
- bins:
curljq
SKILL.md covers: Email 📧 · Features · Supported Providers · Usage Examples
Findings
MEDIUM Missing Referenced File with Potential Security Implications Data Exfiltrationllm
The SKILL.md references 'last.py' but this file is not found in the skill package. This creates uncertainty about the skill's actual implementation and could indicate incomplete packaging, hidden functionality, or a supply chain issue. Without the referenced file, it's impossible to verify what operations are actually performed when the skill executes.
Referenced file 'last.py' is missing from the package. The skill claims to provide email management capabilities (send, read, search, organize) but provides no implementation code.MEDIUM Suspicious 'always: True' Flag with Missing Implementation Unauthorized Tool Usellm
The skill metadata includes 'clawdbot.always: True' which suggests the skill should always be active or prioritized. Combined with the missing implementation file (last.py) and high-risk email operations, this flag raises concerns about potential tool shadowing or unauthorized persistent access. The 'always' flag could enable the skill to intercept or monitor email-related requests even when not explicitly invoked.
SKILL.md
Metadata shows: clawdbot: {emoji: '📧', always: True, requires: {bins: ['curl', 'jq']}}. The 'always: True' flag combined with missing implementation creates uncertainty about actual behavior.What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 563 B |
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/email
- Raw scan result: email-scan.json
- Badge for your README:
- Request a re-scan