pipedrive
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-06.
The Pipedrive CRM skill is a legitimate integration tool for managing Pipedrive API operations through bash scripts. The skill's primary security concern is the instruction to store API credentials in a plaintext configuration file without security guidance. The code itself does not contain malicious patterns - it performs standard API operations (CRUD operations on deals, contacts, organizations, etc.) using curl commands with proper authentication. The bash script reads credentials from either environment variables or the config file, which is normal behavior. The skill does not attempt prompt injection, data exfiltration to unauthorized endpoints, command injection, or other malicious activities. The referenced API documentation file (references/api.md) contains legitimate Pipedrive API reference material. The main improvements needed are: (1) adding security guidance for credential storage, (2) declaring the allowed-tools field for transparency, and (3) including missing referenced files or removing their references. Overall, this is a functional CRM integration skill with minor security hygiene issues rather than active threats.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Pipedrive CRM API for managing deals, contacts (persons), organizations, activities, leads, pipelines, products, and notes. Use for sales pipeline management, deal tracking, contact/organization management, activity scheduling, lead handling, or any Pipedrive CRM tasks.
- Package
- 3 files, 56 KB
- SKILL.md
- 470 words, 12+ sections
- Code
- Shell (1)
SKILL.md covers: Pipedrive · Setup · Quick Reference · Deals (most important!) · Persons (contacts) · Organizations · Activities · Pipelines & Stages · Leads · Products · Notes · Deal Statuses
Findings
MEDIUM Hardcoded credential path in configuration instructions Data Exfiltrationllm
The SKILL.md instructions direct users to store their Pipedrive API token in a plaintext JSON file at ~/.clawdbot/clawdbot.json without any mention of file permissions, encryption, or security considerations. This creates a risk of credential exposure if the file permissions are not properly restricted or if the system is compromised.
SKILL.md
Store in `~/.clawdbot/clawdbot.json`:
```json
{
"skills": {
"entries": {
"pipedrive": {
"apiToken": "YOUR_API_TOKEN"
}
}
}
}What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 4.5 KB |
references/api.md | doc | 9.3 KB |
scripts/pipedrive.sh | script | 42 KB |
External hosts referenced
api.pipedrive.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
ORG_ID PERSON_ID DEAL_ID STAGE_ID PIPELINE_ID EMAIL PIPEDRIVE_API_TOKEN USER_ID API_URL
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/pipedrive
- Raw scan result: pipedrive-scan.json
- Badge for your README:
- Request a re-scan