Typefully
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: typefully-social-media Version: 0.1.0 The skill bundle is classified as **benign**. The `SKILL.md` file is exceptionally well-crafted to prevent prompt injection and misuse by the AI agent. It explicitly forbids the agent from searching for API keys in sensitive locations (e.g., macOS Keychain, `.env` files, system folders), constructing complex shell commands to find credentials, or writing notes to local files instead of the designated `--scratchpad` API option. It also includes strong automation guidelines to prevent spamming or unauthorized actions. The `scripts/typefully.js` script, which is the core logic, uses only built-in Node.js modules and interacts solely with the Typefully API (`api.typefully.com`). It handles API keys and configuration in a secure manner, prioritizing environment variables and offering to integrate local configuration files with `.gitignore` to prevent accidental exposure. Input arguments are parsed and validated, and there are no apparent shell injection vulnerabilities. The `sanitizeFilename` function is a good security practice. A minor functional bug was identified in `cmdMediaUpload` where the `Content-Type` header is explicitly *not* set during S3 uploads, which could lead to incorrect media handling or upload failures, but this is a functional flaw, not indicative of malicious intent or a security vulnerability. There is no evidence of data exfiltration, persistence mechanisms, or other malicious activities.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If TYPEFULLY_API_BASE is set incorrectly or maliciously in the environment, the user's Typefully API key and social-post content could be sent to a non-Typefully endpoint.
The CLI sends the Typefully bearer token to a base URL controlled by an environment variable that is not declared in the registry metadata or setup requirements.
const API_BASE = process.env.TYPEFULLY_API_BASE || 'https://api.typefully.com/v2'; ... 'Authorization': `Bearer ${apiKey}` ... fetch(`${API_BASE}${endpoint}`, options);Unset TYPEFULLY_API_BASE unless deliberately using a trusted test endpoint, and prefer validating or pinning the API host. The skill metadata should declare its API key and endpoint-related environment variables.
The skill can publish or schedule public social media content on connected accounts when used for those tasks.
The documented workflow includes immediate publishing through the Typefully CLI.
"Post this now" | `drafts:create ... --schedule now` or `drafts:publish <draft_id> --use-default`
Before publishing, confirm the final text, media, platform, and social set/account, especially when a default social set is configured.
It is harder for a user to verify that the bundled script matches the intended upstream Typefully skill.
The registry metadata does not provide a verified source or homepage, even though the skill itself references a GitHub source.
Source: unknown Homepage: none
Compare the included files against the referenced upstream repository before trusting the skill with a Typefully API key.