Back to skill

Security audit

Rotifer Self-Evolving Agent

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the findings are treated as purpose-related, while some installation and credential-handling details remain noted and the scan was partial.

The verdict is benign, not a guarantee of zero risk. Before installing, consider the documented `npx` server and its service requests, and whether the described login token handling fits your needs. Coverage is incomplete: although all three listed components were scanned, Skillspector could not resolve several path-like references.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 93)May include surrounding context.

md
ends an anonymous heartbeat each time it runs a Gene — a random machine id, the channel and the CLI version, nothing else; `ROTIFER_TELEMETRY=0` or `DO_NOT_TRACK=1` stops it too. Argument values, file contents, environment variables and your local configuration are not sent. |
| **Credentials** | It does not read your environment variables or other tools' secrets, and it cannot log you in or out. Public data needs no login. If you log in yourself with `rotifer login`, the session token is saved to `~/.rotifer/credentials.json` with `0600` permissions. The MCP server then attaches it to its Rotifer API requests and usage records, and renews it there when it expires, writing the new token back to the same file. It is not shown to the assistant and is sent nowhere else. Genes and Agents do not live there — they are project files. |

**Every replacement is confirmed by you.** `/evolve` and `/evolve status` only
read and report. `/evolve upgrade` proposes a specific swap and waits — no Gene

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

md
Public Gene and Arena data needs no login: the MCP server reads it with the **Supabase anon key** (a public, client-safe key protected by Row Level Security). It does not read your environment variables, nor secrets belonging to any other tool.

This Skill cannot log you in or out: neither `login` nor `logout` is in its tool set, and none of its ten tools hands a token to the assistant. Logging in happens outside it, with `rotifer login` in a terminal, which saves a session token to `~/.rotifer/credentials.json` with `0600` permissions; `rotifer logout` deletes it. When that file exists, the MCP server uses it for three things and nothing else: it attaches the token to its requests to the Rotifer API (so your own unpublished Genes are visible to you), it labels the usage record described above with your user id, and when the token has expired it renews it at the Rotifer API's sign-in endpoint and writes the renewed token back to the same file. The token is sent nowhere else. Genes and

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding

Shadow Command Trigger: description clause 'Invoked explicitly via /evolve — scan local capabilities, compare Genes, inspect fitness scores, replace weak ones with user approval (each replacement can be rolled back), write an Agent definition into the project (/evolve create-agent), and execute a local Agent's Genes in the WASM sandbox (/evolve run-agent)' conflicts with built-in command 'write'

Content

No source excerpt is available for this finding.