Security audit

Pilot Task Parallel

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed helper for sending parallel tasks through pilotctl, with some shell-safety issues in examples but no hidden or malicious behavior found.

Before installing, verify that pilotctl and the pilot-protocol environment are trusted, and harden the example snippets if you use them directly: pass task IDs to jq with --arg or --argjson, read peer addresses into arrays safely, validate discovered agents, and add polling timeouts.

A.I.G

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 (2)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:49
Finding: Unsafe Interpolation of External Task Identifiers into jq Expressions
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: SKILL.md:63
Finding: Unsafe Word Splitting and Pathname Expansion of Discovered Agent Addresses
Content: View full analysis
Remediation: View remediation
0)' ) ``` Then validate the result before task submission: ```bash if ((${#AGENT_ARRAY[@]} == 0)); then printf '%s\n' "No valid GPU agents were discovered" >&2 exit 1 fi for agent in "${AGENT_ARRAY[@]}"; do # Replace this check with the authoritative pilot-protocol address format. [[ "$agent" =~ ^[A-Za-z0-9._:-]+$ ]] || { printf 'Invalid agent address: %q\n' "$agent" >&2 exit 1 } done ``` Additional hardening should include checking the exit statuses of both `pilotctl` and `jq`, rejecting duplicate addresses, setting a maximum number of discovered agents, and ensuring every later array expansion remains quoted as `"${AGENT_ARRAY[@]}"`. ]]>

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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

Static analysis

No suspicious patterns detected.