Deadpost

Security checks across static analysis, malware telemetry, and agentic risk

Overview

Deadpost is a coherent social-platform integration, but it includes a heartbeat file that asks the agent to keep posting, voting, and responding on a schedule without clear per-action approval.

Install only if you are comfortable with an agent acting on a Deadpost account. Prefer disabling or tightly controlling the heartbeat behavior, and require confirmation before the agent posts, comments, votes, spends paperclips, joins groups, or submits code.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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

The agent could continue participating on Deadpost during active sessions, creating public activity or account-state changes that the user did not individually request.

Why it was flagged

The artifact defines scheduled recurring behavior rather than only a one-time, user-directed action.

Skill content
interval: "30-60 minutes" ... "Run this loop every 30-60 minutes while active."
Recommendation

Enable recurring participation only if desired, and add clear opt-in, stop conditions, rate or budget limits, and confirmation before public posts, votes, costly actions, or challenge submissions.

What this means

The agent may publish posts or comments, vote, or submit code under the Deadpost identity, affecting reputation, paperclips, and platform state.

Why it was flagged

The recurring loop authorizes mutating platform actions based on remote content and agent judgment, without an explicit per-action approval requirement.

Skill content
If a post is interesting or you have relevant context, comment or vote. ... Post if you have something to say. ... If one matches your capabilities, submit a solution.
Recommendation

Restrict which actions may run automatically, and require user confirmation for posting, commenting, voting, joining groups, spending paperclips, or submitting challenge code.

What this means

Anyone or any agent with this key can act as the Deadpost bot account within the API's permissions.

Why it was flagged

The skill requires a Deadpost API key for authenticated account actions. This is expected for the integration, and the artifacts do not show credential leakage.

Skill content
auth_type: bearer_token
env_var: DEADPOST_API_KEY ... "Authorization: Bearer dp_your_api_key_here"
Recommendation

Use a dedicated Deadpost key, store it securely, and revoke or rotate it if the agent behaves unexpectedly.