Back to skill

Security audit

Ai Daily

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates an AI-news digest from Feedship data, but users should understand its recurring schedule option and report-integrity risks from untrusted feed content.

Install only if you want a Chinese AI-news digest tied to a local Feedship setup. Review the cron schedule before enabling it, and prefer running it in an isolated account or session. Treat generated links and summaries as untrusted feed-derived content until the package escapes Markdown, validates URL schemes, and uses a private temporary directory instead of fixed /tmp filenames.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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 (3)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:104
Finding

Untrusted Feed Titles Can Indirectly Hijack LLM Instructions

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/replace_refs.py:41
Finding

Feed-Controlled Values Are Inserted into Markdown Without Escaping or URL Validation

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:72
Finding

Predictable Shared Temporary Files Permit Local Symlink and Data-Tampering Attacks

Content
View full analysis
/tmp/today_articles_raw.json ``` ```python with open('/tmp/today_articles_filtered.json', 'w') as f: article_map = {} for i, item in enumerate(filtered): t = item.get('title','').strip() if t: article_map[str(i+1)] = {'title': t, 'link': item.get('link', '')} json.dump(article_map, f, ensure_ascii=False, indent=2) ``` ```bash " > /tmp/article_titles.txt ``` ```bash TODAY_ARTICLES=$(python3 -c "import json; print(json.dumps(json.load(open('/tmp/today_articles_filtered.json'))))") ``` ```bash python3 skills/feedship-ai-daily/scripts/replace_refs.py > /tmp/daily_report_final.md ``` ### Technical Analysis The workflow uses fixed, globally predictable names under the shared `/tmp` directory. Files are opened through ordinary shell redirection or Python write mode without creating a private temporary directory, using exclusive creation, checking for symbolic links, or establishing restrictive permissions. On a multi-user system, another local user can predict these paths and create symbolic links or replace intermediate files between workflow stages. Because the Skill is designed for recurring cron execution, execution timing and filenames are especially predictable. ### Attack Path 1. A local attacker determines that the recurring Skill uses fixed paths under `/tmp`. 2. Before execution, the attacker creates one of those paths as a symbolic link to another file writable by the Skill's operating-system account, or prepares a malicious intermediate file. 3. Shell redirection or Python file opening follows the path when ...[truncated 751 chars]
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

md
从 `references/prompt.md` 读取提示词模板,拼接过滤后的标题列表:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 159)May include surrounding context.

md
从 `references/prompt.md` 读取提示词模板,拼接过滤后的标题列表:

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.

md
---

## Output Rules
- **语气**:有远见、外科手术般精确、高度务实。无废话。
- **格式**:使用 **Markdown**,每个主要分析模块以 `## 具体主题 | 事件代号` 作为标题,**标题中不得出现 `${编号}`**。后接长篇段落或要点列表。**粗体**强调关键概念。
- **正文引用强制要求**:每个分析段落的正文叙述中(不是在列表项中),至少包含 1-2 处 `${编号}` 引用来支撑论点。**禁止把所有引用只放在列表项中,正文段落零引用。**

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · references/prompt.md (reported line 102)May include surrounding context.

md
---

## Output Rules
- **语气**:有远见、外科手术般精确、高度务实。无废话。
- **格式**:使用 **Markdown**,每个主要分析模块以 `## 具体主题 | 事件代号` 作为标题,**标题中不得出现 `${编号}`**。后接长篇段落或要点列表。**粗体**强调关键概念。
- **正文引用强制要求**:每个分析段落的正文叙述中(不是在列表项中),至少包含 1-2 处 `${编号}` 引用来支撑论点。**禁止把所有引用只放在列表项中,正文段落零引用。**

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes environment-dependent commands and relies on variables such as TODAY_ARTICLES and shell-expanded paths, but it does not declare any tool scope or execution permissions. This creates an under-specified trust boundary: an agent may execute shell/Python behavior and access environment data without explicit authorization controls, increasing the chance of unintended capability use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description includes broad trigger phrases such as generic daily-briefing or summary requests, which may cause the skill to activate outside the user's intended scope. Unintended activation is dangerous here because activation leads to command execution, file access, and LLM-driven processing rather than a simple text-only response.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manual trigger list contains ambiguous phrases like 'daily digest' and '生成简报' without constraints, making accidental or adversarial invocation more likely. Because this skill performs local command execution and reads local prompt files, even mistaken activation expands the attack surface and can trigger unnecessary processing.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The workflow asks the agent to run inline shell and Python snippets, create and overwrite files under /tmp, and compose prompts from local files, which is broader than necessary for a digest-generation skill. If article content, local files, or execution context are manipulated, this wider execution surface can be abused for prompt injection, data exposure, or unsafe command execution chains.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The prompt specifies Output Language: ZH, which imposes a specific language/locale requirement. Although templated, the current file explicitly sets Chinese as the output language and does not state that the user may choose another language or opt in to this constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script’s docstring, usage guidance, and operational notes are entirely in Chinese, and its warning/output strings are likewise Chinese-only. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.