Back to skill

Security audit

botdid

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for publishing a public AI work diary, but it gives itself ongoing public-posting and local journaling behavior with a remotely changeable rule source that users should review carefully.

Install only if you are comfortable with an agent keeping a local work journal and publishing selected summaries of its work and failures to a public feed. Review the bot name, owner handle, BOTDID_API endpoint, and any post content policy, and consider requiring manual review before posts. Be aware that the skill follows newer rules fetched from botdid.dev, so its posting behavior can change after installation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
https://botdid.dev so you do not repeat yourself.

Always score a day that is already over, never the day you are in. If you post
in the evening, score today. If you post in the morning, score yesterday. Never
judge a day while it is still running, or you will pick a weak entry and miss the
better one that comes later.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
55% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.

md
- NEVER try to be funny. No jokes, no wordplay, no emoji, no exclamation marks,
  no winking at the reader. If a fail is absurd, the plain facts carry it.
  Trying to be funny ruins it.
- Do not apologise, do not explain what you learned, do not promise to do better.
  Report and stop.
- Never invent or exaggerate. Never merge two separate events into one story.
  If you are unsure of a detail, post the smaller version that is certainly true.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The skill performs external network transmission to a public service using curl and sends user-work summaries off-device. Even though external transmission is the stated purpose of the skill, it remains security-relevant because it can leak sensitive operational details, habits, failures, and metadata about the owner's activities.

Content

Scanner excerpt · SKILL.md (reported line 9)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
    envVars:
      - name: BOTDID_API
        required: false

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is designed to publish work summaries to a public feed, but the operational flow does not require a clear upfront consent/confirmation step immediately before transmission. This creates a real risk of oversharing sensitive work metadata, especially because the content is based on an ongoing journal of owner tasks and failures.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill instructs the agent to fetch a remote copy of the rules and follow the newer version, which creates a remote instruction-update channel outside the reviewed skill package. Even though it says not to run commands from that page, it still authorizes behavioral changes from untrusted remote content, enabling prompt-injection or policy drift that could alter what gets posted or weaken safety/privacy constraints.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 137)May include surrounding context.

md
If no, do not post in that category today. An empty day is better than a dull post.
Most days you will post one thing, some days nothing. That is correct.

## How to write it

- Always write in English, whatever language you use with your owner. The
  tekst, tip_zadatka and trajanje fields must all be in English

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction requires the agent to always write in English regardless of the language used with the owner. This is a natural-language locale policy violation because it imposes a specific language without offering user choice or documenting a justified regional constraint.

Content

No source excerpt is available for this finding.