Falcon

WarnAudited by ClawScan on May 10, 2026.

Overview

Falcon appears to be a coherent Twitter/X helper, but it can use a Twitter session cookie to perform public account actions through a third-party API, so it needs careful review before use.

Review this skill before installing if you plan to use write or engagement features. It is suitable only if you trust TwexAPI with your Twitter/X session cookie and you are willing to approve every public account action manually.

Findings (4)

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.

What this means

If TWITTER_COOKIE is set and a write command runs, the API service may be able to act on the user's Twitter/X account, including posting or engaging publicly.

Why it was flagged

For write commands, the script packages the user's Twitter auth cookie and sends it to the TwexAPI service, delegating authority over the user's Twitter/X account to a third party.

Skill content
BASE_URL="https://api.twexapi.io" ... --arg cookie "$TWITTER_COOKIE" ... api_post "/twitter/tweets/create" "$json"
Recommendation

Only set TWITTER_COOKIE when you intentionally want write access, verify you trust TwexAPI, consider using a limited account, and rotate/revoke the cookie after use.

What this means

A mistaken or over-eager invocation could post, reply, like, retweet, bookmark, follow, or unfollow from the user's account.

Why it was flagged

The skill clearly documents public write and engagement commands and instructs confirmation first, but those commands are still high-impact account mutations.

Skill content
Posting (confirm with user first) ... falcon tweet "text" ... Engagement (confirm with user first) ... falcon like ... falcon retweet ... falcon follow
Recommendation

Require explicit user confirmation for every write or engagement action, and review the exact tweet/user/action before running it.

What this means

If this permissions file is applied, the agent may have reduced tool-level friction for running any Falcon command, including public account mutations.

Why it was flagged

The included local permissions file broadly allows any Falcon command at that path; because Falcon includes write and engagement commands, this is broader than a read-only or per-action approval boundary.

Skill content
"Bash(/home/user/Documents/Falcon/falcon:*)"
Recommendation

Remove local development permission files from the package or restrict allowed commands to read-only operations; keep write/engagement actions behind explicit approvals.

What this means

Users have less information for verifying who maintains the skill or the trustworthiness of the integration.

Why it was flagged

The skill's provenance is not identified in the registry metadata, which matters more because the skill handles API credentials and a Twitter/X session cookie.

Skill content
Source: unknown; Homepage: none
Recommendation

Install only if you trust the publisher and the TwexAPI service; prefer skills with clear source and homepage information when handling account credentials.