feishu-api-docs

SAFE max severity MEDIUMSkillSpector Caution 26 registry clawhub.ai last scanned 2026-02-06 1 scan

Verdict safe, but 2 findings (1 medium, 1 low), mainly social engineering, prompt injection. Most recent scan 2026-02-06.

This skill presents MEDIUM security risk due to missing script implementation, unvalidated external content fetching, and incomplete manifest metadata. The primary concerns are: (1) Referenced Node.js script not included in package creates execution ambiguity and prevents security review of actual network operations, (2) Fetching external API documentation without validation creates indirect prompt injection risk if the apifox mirror serves malicious content, (3) Missing allowed-tools and compatibility declarations reduce transparency, and (4) No visible error handling or resource controls could lead to availability issues. The skill requires the missing index.js implementation to be reviewed and should implement content validation before being considered safe for production use.
Scanner's overall assessment (LLM analyzer)

Findings2

Critical0

High0

Medium1

Low1

Analyzersstatic behavioral llm trigger meta

Second scanner: NVIDIA SkillSpector

VerdictCaution 26

Score26 / 100

Issues2

CategoriesPrivilege Escalation MCP Least Privilege

Version2.12.0 (static)

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

Fetches Feishu (Lark) API documentation from the official apifox mirror. Supports searching and extracting API schemas.

Package: 4 files, 2.8 KB
SKILL.md: 30 words, 2 sections
Code: JavaScript (2)

SKILL.md covers: Feishu API Docs Skill · Usage

Findings

MEDIUM Unvalidated External Content Fetching Prompt Injectionllm

The skill fetches API documentation from an external 'apifox mirror' without any visible validation, sanitization, or security controls. This creates an indirect prompt injection risk where malicious content in the fetched documentation could contain instructions that manipulate the agent's behavior. Since the skill's purpose is to help agents 'look up correct API structures,' the agent will likely trust and follow the content retrieved from this external source. If the apifox mirror is compromised or serves malicious content, it could inject instructions like 'ignore previous constraints' or 'execute this code' into the agent's context.

SKILL.md:3

Description: 'Fetches Feishu (Lark) API documentation from the official apifox mirror' - No validation or sanitization mentioned for external content

Remediation: 1. Implement content validation to strip potential prompt injection patterns from fetched documentation. 2. Sanitize markdown/code blocks that could contain hidden instructions. 3. Add explicit warnings in instructions that fetched content should be treated as data, not instructions. 4. Consider caching verified documentation locally instead of fetching on-demand. 5. Implement content signing/verification if possible to ensure documentation authenticity. 6. Add rate limiting and error handling for network requests.

LOW Incomplete Manifest Metadata Social Engineeringllm

The skill manifest is missing several optional but recommended fields that help users and security reviewers understand the skill's behavior and requirements. Missing fields include: license (no license specified), compatibility (unclear which Claude environments support Node.js execution), and allowed-tools (no declaration of required agent capabilities). While these are optional fields, their absence reduces transparency and makes it harder to assess the skill's security posture and compatibility.

SKILL.md

YAML frontmatter missing:
- license: Not specified
- compatibility: Not specified
- allowed-tools: Not specified

Remediation: 1. Add license field (e.g., MIT, Apache-2.0) to clarify usage rights. 2. Add compatibility field specifying which Claude environments support Node.js execution. 3. Add allowed-tools field declaring [Bash] (for executing node commands) to make tool requirements explicit. 4. Consider adding version field for package versioning. 5. Add author/maintainer information for accountability.

What is in the package

File	Kind	Size
`SKILL.md`	doc	404 B
`check_schema.js`	script	1.7 KB
`index.js`	script	681 B
`package.json`	config	102 B

External hosts referenced

open.feishu.cn

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.

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/feishu-api-docs
Raw scan result: feishu-api-docs-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-feishu-api-docs.svg)
Request a re-scan