Back to skill

Security audit

storyforge-writing

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed StoryForge writing workflow skill that creates and validates project-local files, with no evidence of credential use, persistence, network payloads, or hidden destructive behavior.

Install this if you want a Chinese-language StoryForge structured writing workflow and are comfortable letting the agent create or update project-local JSON, provenance, and manifest files. Review the target project directory before running write steps, and treat any DaVinci or media-generation integration notes as optional environment-specific guidance that should require explicit user direction.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (30)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This finding goes beyond harmless description drift because the skill also instructs running automated tests, invoking subprocess-based tooling, and performing file creation/deletion/copying operations that are not plainly disclosed in the high-level purpose statement. In an agent setting, undisclosed execution and filesystem mutation increase the risk of overbroad actions, accidental data loss, or execution of repository-resident code the user did not expect to run.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This finding goes beyond harmless description drift because the skill also instructs running automated tests, invoking subprocess-based tooling, and performing file creation/deletion/copying operations that are not plainly disclosed in the high-level purpose statement. In an agent setting, undisclosed execution and filesystem mutation increase the risk of overbroad actions, accidental data loss, or execution of repository-resident code the user did not expect to run.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

This finding goes beyond harmless description drift because the skill also instructs running automated tests, invoking subprocess-based tooling, and performing file creation/deletion/copying operations that are not plainly disclosed in the high-level purpose statement. In an agent setting, undisclosed execution and filesystem mutation increase the risk of overbroad actions, accidental data loss, or execution of repository-resident code the user did not expect to run.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

md
表名、索引与全字段查 `references/schema-tables.md`(§2 全表索引 123 张 = 表名单源;§4 全表字段清单 106 表)。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

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

md
表名、索引与全字段查 `references/schema-tables.md`(§2 全表索引 123 张 = 表名单源;§4 全表字段清单 106 表)。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file is written entirely in Chinese and does not indicate any language choice, alternative locale, or justification for a locale-specific constraint. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file contains user-facing operational instructions solely in Chinese, including safety-relevant guidance about validation, publishing, and write-back procedures. Under the language/locale policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is written entirely in Chinese and presents the workflow and operational guidance only in that language. Under the policy, a skill should not force a specific language or locale unless it offers user choice or clearly documents a justified region/language constraint, which this README does not do.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill explicitly instructs the agent to read and write project files and execute Python validation scripts, but it does not declare an explicit tool/permission scope. In an agent environment, that gap weakens policy enforcement and user visibility, making it easier for the skill to access or modify files or invoke shell commands more broadly than intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill’s description and trigger phrases are entirely specified in Chinese, and there is no statement anywhere in the file that users may interact in other languages or choose their preferred locale. Because the skill is presented as a general-purpose writing workflow rather than a region-specific tool, this creates a natural-language locale constraint without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This contract file presents all operational guidance in Chinese and does not state that the skill is Chinese-only, region-specific, or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Lines L6-L7 include natural-language content only in Chinese ("只选入本章出场的 2 名角色", "项目内尚无考据库"). For a general manifest, forcing a specific language in user-visible metadata without opt-in or justification can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The title and surrounding documentation are explicitly written in Chinese, presenting the registry as a Chinese-only reference. Under the language/locale policy, this is a natural-language constraint unless the skill offers a language choice or clearly documents a justified locale limitation, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill reference is written only in Chinese and presents its conventions as mandatory for the referenced agent environment, without any indication that users may choose another language or locale. This can violate language/locale policy when the skill is used by users who have not opted into Chinese.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The code imports subprocess and executes check_framework_artifact.py --list-codes, which is a shell-adjacent operation with side effects on process execution. Although the surrounding comments explain the consistency check's purpose, there is no user-facing disclosure, confirmation, or runtime notice near this operation indicating that another script will be launched.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/check_consistency.py (reported line 510)May include surrounding context.

python
chk = os.path.join(ROOT, "scripts", "check_framework_artifact.py")
    try:
        import subprocess
        out = subprocess.run([sys.executable, chk, "--list-codes"], capture_output=True, text=True, timeout=60).stdout
        codes = {l.split()[0] for l in out.splitlines() if l.strip()}
    except Exception as e:  # noqa: BLE001
        codes = set()

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file’s docstring, CLI usage text, diagnostics, and status messages are predominantly hard-coded in Chinese, making the tool effectively locale-specific. There is no visible option to select language or documentation justifying a mandatory Chinese locale, which violates the language/locale policy criterion.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/run_tests.py (reported line 37)May include surrounding context.

python
def run(d, *flags):
    p = subprocess.run([PY, CHECK, "--json", *flags, os.path.join(d, FW)], capture_output=True, text=True)
    try:
        out = json.loads(p.stdout)
        issues = out["artifacts"][0]["issues"]

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/run_tests.py (reported line 48)May include surrounding context.

python
def resign(d):
    """改了主文件后重新生成旁车哈希(保留 sources),模拟「作者按流程刷新旁车」。"""
    subprocess.run([PY, MAKE, os.path.join(d, FW), "--write"], capture_output=True, check=True)


def chapters(fw):

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/run_tests.py (reported line 277)May include surrounding context.

python
print("       实得:", [(i["level"], i["code"]) for i in iss])
            fails += not ok
        # 3) 技能包自检
        p = subprocess.run([PY, os.path.join(ROOT, "scripts", "check_consistency.py"), "--quiet"],
                           capture_output=True, text=True)
        ok = p.returncode == 0
        print("[%s] check_consistency.py" % ("PASS" if ok else "FAIL"))

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The notice is written entirely in Chinese, including headings and explanatory text, with no indication that another language is available or that the locale restriction is required for a region-specific purpose. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is entirely in Chinese and does not mention any user language selection, multilingual support, or justification for enforcing a specific locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file presents its primary instructions and labels in Chinese, including the title and policy content, with no indication that users may choose another language. Under the language/locale policy rule, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file’s natural-language instructions and all evaluation prompts/expectations are written in Chinese, and the note establishes this as the evaluation set behavior without any opt-in or alternative locale. For a generally applicable skill artifact, this can be a language-policy issue because it implicitly fixes one language for use and review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese ('角色', character names) and does not indicate that the skill is region-specific or that users can opt into a preferred language. That can violate a language/locale policy requiring neutral defaults or user choice.

Content

No source excerpt is available for this finding.