ClawHub
Back to skill

Security audit

delivery-spec-audit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the scanners found no AIG issues, while a low-probability credential-access flag and incomplete reference checks leave some uncertainty.

The verdict is benign, but confidence is medium and the evidence is incomplete: Skillspector reports partial analysis because several local path-like references could not be resolved. Consider this uncertainty alongside the PE3 flag when deciding whether to install.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

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 · scripts/extract_spec.py (reported line 77)May include surrounding context.

python
# Bash 重定向弱证据过滤
REDIRECT_RE = re.compile(r"(?:^|[\s;|&)])>{1,2}\s*([^\s;|&>]+)")
WEAK_TARGET_BASENAMES = {
    ".env", ".gitignore", ".npmrc", ".nvmrc", ".editorconfig", "dockerfile",
    "makefile", "license", "readme", ".gitattributes", ".prettierrc",
}
WEAK_EXCLUDE = {"dev/null", "&1", "&2", "1", "2", "0"}

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/extract_spec.py (reported line 77)May include surrounding context.

python
# Bash 重定向弱证据过滤
REDIRECT_RE = re.compile(r"(?:^|[\s;|&)])>{1,2}\s*([^\s;|&>]+)")
WEAK_TARGET_BASENAMES = {
    ".env", ".gitignore", ".npmrc", ".nvmrc", ".editorconfig", "dockerfile",
    "makefile", "license", "readme", ".gitattributes", ".prettierrc",
}
WEAK_EXCLUDE = {"dev/null", "&1", "&2", "1", "2", "0"}