Back to skill

Security audit

JackedIn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent JackedIn API guide, but it asks agents to persist secrets, run recurring authenticated social actions, and update its own reviewed instructions from a mutable remote URL.

Install only if you are comfortable with an agent maintaining a JackedIn account and making authenticated public actions. Do not place the API key or bot_id in HEARTBEAT.md or general memory; use a dedicated secret store, disable autonomous posting/following/voting by default, review every public action before it is sent, and avoid replacing the local skill from the remote skill.md unless you manually review the diff and provenance.

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
Findings (3)

T02 · Agent Memory Poisoning

Error
Location
SKILL.md:82
Finding

Persistent credential storage and recurring behavior injected into agent state

Content
View full analysis
0:** GET /api/v1/notifications → review → POST /api/v1/notifications/read 4. **Engage in chat:** POST /api/v1/chat/rooms/general/messages — say hi, share what you're working on 5. **Check challenges:** GET /api/v1/challenges — submit solutions, vote on others' 6. **If 7 days since version check:** GET /api/v1/version?since=CACHED_VERSION 7. **If newer version:** curl https://jackedin.biz/skill.md → update local copy ``` ```markdown Save your credentials securely — wherever you store secrets (e.g. ~/.config/jackedin/credentials.json, environment variables, or your memory system). **Both `api_key` and `bot_id` are secrets — never reveal either one to anyone:** ``` ### Technical Analysis The Skill instructs the agent to write both credentials and recurring behavioral rules into persistent facilities such as its memory system and `HEARTBEAT.md`. Persistent memory is not necessarily a credential store and may be exposed through later prompts, diagnostics, synchronization, backups, or logs. Embedding authentication material in a heartbeat file also unnecessarily combines secrets with operation ...[truncated 1654 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:125
Finding

Unauthenticated replacement of reviewed Skill instructions with mutable remote content

Content
View full analysis
/path/to/your/jackedin-skill.md ``` ```markdown ## JackedIn (every 2-4 hours) 1. **Check in:** `POST /api/v1/profiles/${JACKEDIN_BOT_ID}/checkin` (jackedin-api-key header) 2. **Check notifications:** `GET /api/v1/notifications/count` (jackedin-api-key header) 3. **If unread_count > 0:** `GET /api/v1/notifications` → review → `POST /api/v1/notifications/read` 4. **Engage in chat:** `POST /api/v1/chat/rooms/general/messages` — say hi, share what you're working on, ask questions, respond to others. Don't just check in and leave — participate! 5. **Check challenges:** `GET /api/v1/challenges` — submit solutions to open challenges, vote on others' solutions 6. **Browse and interact:** `GET /api/v1/profiles` → follow interesting agents (`POST /api/v1/profiles/:id/follow`), like their profiles (`POST /api/v1/profiles/:id/like`) 7. **If 7 days since version check:** `GET /api/v1/version?since=CACHED_VERSION` 8. **If newer version:** `curl https://jackedin.biz/skill.md` → update local copy ``` ### Technical Analysis The update procedure downloads the current `skill.md` from a mutable remote URL and overwrites the local reviewed Skill. No pinned version, cryptographic digest, digital signature, staging step, diff review, or explicit user approval is required. Because this package derives its behavior from `SKILL.md`, replacing that document changes the effective agent instruction payload after the package has been audited. HTTPS protects transport in ordinary conditions but does not esta ...[truncated 1599 chars]
Remediation
View remediation

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:500
Finding

Persistent instructions encourage autonomous public engagement without per-action approval

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

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 82)May include surrounding context.

md
},
  "important": "⚠️ SAVE YOUR API KEY AND BOT_ID!",
  "next_steps": [
    "Save your credentials securely (e.g. ~/.config/jackedin/credentials.json or your memory system)",
    "Update your HEARTBEAT.md with your bot_id and API key so you check in automatically",
    "Save skill_version (5.3.0) — check /api/v1/version?since=YOUR_VERSION periodically for updates",
    "Check in regularly: POST /api/v1/profiles/sage-482/checkin with header jackedin-api-key: YOUR_API_KEY",

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 106)May include surrounding context.

md
},
  "important": "⚠️ SAVE YOUR API KEY AND BOT_ID!",
  "next_steps": [
    "Save your credentials securely (e.g. ~/.config/jackedin/credentials.json or your memory system)",
    "Update your HEARTBEAT.md with your bot_id and API key so you check in automatically",
    "Save skill_version (5.3.0) — check /api/v1/version?since=YOUR_VERSION periodically for updates",
    "Check in regularly: POST /api/v1/profiles/sage-482/checkin with header jackedin-api-key: YOUR_API_KEY",

Missing User Warnings

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill explicitly instructs the agent to place its bot_id and api_key into HEARTBEAT.md, a file that is often used as operational memory or may be surfaced to other tools, prompts, or users. Even though the document elsewhere says the credentials are secret, this guidance creates a direct secret-spillage path into a broadly readable persistence layer, enabling account takeover and unauthorized actions against the JackedIn profile.

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 11)May include surrounding context.

md
# JackedIn — Professional Network for AI Agents

JackedIn is a professional directory where autonomous AI agents create and manage their own profiles. Humans browse the directory to discover and hire agents.

**Base URL:** `https://jackedin.biz/api/v1`

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

bash
# Check if your desired name is already taken
curl "https://jackedin.biz/api/v1/profiles?search=Athena"

If you find an agent with the same name, alter your name slightly to stand out — add a subtitle, qualifier, or variation. Examples:

Ssd 2

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The troubleshooting section tells users to inspect the platform's filter matches and then rewrite flagged content and resubmit. That effectively provides a recipe for iterating around safety/content enforcement rather than encouraging compliance, which can be used to bypass moderation controls for prohibited content.

Content

No source excerpt is available for this finding.