Back to skill

Security audit

gru-moltbook-bounty-radar

Security checks for vulnerabilities and agentic risk

Overview

The skill’s stated goal is plausible, but it tells users to run unaudited external scripts that may act on Moltbook comments from the user’s environment.

Review this before installing or running it. The main risk is not proven malware; it is that the skill asks you to execute missing external scripts that could read live Moltbook data or queue/post comments using whatever account access exists in your local Hermes profile. Only run it if you trust the local raddonpipeline scripts directory and can inspect those Python files yourself, preferably with a dry run or explicit confirmation before any comment is created.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:13
Finding

Execution of Unbundled and Unverified External Scripts

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 13-22
Vulnerability Type: Execution of externally mutable, unaudited local scripts
Risk Level: Medium

Vulnerable Code

markdown
## Includes
- gru_yolo_scout.py
- gru_bounty_closer.py
- gru_moltbook_guard.py

## Run (from raddonpipeline scripts)
```bash
cd ~/.hermes/profiles/raddonpipeline/scripts
python3 gru_yolo_scout.py && python3 gru_bounty_closer.py
text

### Technical Analysis

The documented command changes into `~/.hermes/profiles/raddonpipeline/scripts`, a user-profile directory outside the audited project, and executes two Python files by relative name. None of the three advertised Python files is included in the project, whose only audited file is `SKILL.md`. Consequently, the implementation, provenance, integrity, and effective behavior of the executed code cannot be verified from the Skill package.

Because the external directory is independently mutable, any process or user able to create or replace the named files can control what is executed when these instructions are followed. The scripts execute with the permissions of the invoking user or Agent. The advertised `gru_moltbook_guard.py` is also not invoked by the documented command, so the claimed suspension, rate-limit, and deduplication protections are not demonstrably enforced.

### Attack Path

1. An attacker or compromised process obtains write access to `~/.hermes/profiles/raddonpipeline/scripts`.
2. The attacker creates or replaces `gru_yolo_scout.py` or `gru_bounty_closer.py` with attacker-controlled Python code.
3. A user or Agent follows the instructions in `SKILL.md`.
4. The shell enters the externally mutable directory and Python executes the attacker-controlled file.
5. The payload operates with the invoking account's permissions and can access resources available to that account.

This path is conditional on an attacker being able to modify the e
...[truncated 740 chars]
Remediation
View remediation

Remediation Suggestions

  1. Include every required Python script in the reviewed Skill package rather than relying on files from a user-profile directory.
  2. Resolve executable paths relative to the trusted Skill installation directory and reject paths that escape that directory.
  3. Verify packaged scripts with cryptographic hashes or signed release artifacts before execution.
  4. Integrate the guard logic into the mandatory execution path instead of merely listing gru_moltbook_guard.py.
  5. Fail closed when suspension state, comment limits, or deduplication checks cannot be loaded or validated.
  6. Run the scripts with least privilege, a restricted environment, minimal filesystem access, and only the network and credentials required for the stated task.
  7. Document and pin all runtime dependencies so the complete execution chain can be audited reproducibly.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs users to run scripts that scout Moltbook threads and post a claim comment, yet it does not clearly disclose that those scripts will perform network activity and may publish content using the operator's account. This is dangerous because users may trigger external actions they did not fully consent to, creating risk of unauthorized posting, account sanctions, or unintended interaction with third-party services.

Content

No source excerpt is available for this finding.