T09 · Insecure Skill Coding Practices
- Location
SKILL.md:55- Finding
Shell Command Injection Through Unescaped User-Supplied Topic
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
TweetNugget is a coherent local quote picker, but its instructions can route a user-supplied topic into a Bash command without clear quoting or validation.
Review before installing if your agent may execute skill-provided Bash snippets automatically. The quote data and Python script are local and simple, but the skill should ideally quote or validate topic inputs, map topics to known tags, or avoid shell interpolation entirely.
SKILL.md:55Shell Command Injection Through Unescaped User-Supplied Topic
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
The quick-start phrases are generic everyday requests like 'Give me a quote' and 'Surprise me', which are likely to match ordinary conversation outside an explicit invocation flow. In an agent-skill environment, overly broad triggers can cause unintended activation, leading to unsolicited skill execution and response hijacking when the user did not specifically intend to invoke this skill.
Without declared permissions the skill's intent is opaque and cannot be validated.
The trigger phrases are broad conversational language such as asking for inspiration or wisdom, which can cause the skill to activate in situations the user did not specifically intend. Unintended invocation can override more appropriate handling, produce irrelevant output, or unexpectedly execute the associated tool flow, especially in agents that auto-route based on natural language heuristics.
This JSON file contains natural-language content, and the quote at L443 explicitly frames the statement as applying to 'Men' only. Under the language/locale policy category, this is a natural-language phrasing choice that imposes a gendered framing without justification or opt-in.
At L152 the code uses "" in t, which is true for every string in Python, including non-empty tag values. The comments at L153-L154 explicitly state the opposite and therefore actively contradict the implemented behavior.