Back to skill

Security audit

大项目组织 (project-organization)

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly organizes project folders, but it also includes high-impact repair commands that can change OpenCode project records and remote sync state, so it should be reviewed before installation.

Install only if you want this project-organization workflow and are comfortable with scripts moving files into `.trash`, initializing git, and keeping persistent logs. Treat `oc_project_link.py fix --hub`, `trash.py purge`, and buffer TTL cleanup as administrative actions: review dry-run/status output first, confirm backups, and avoid remote hub cleanup unless you understand the OpenCode sync setup.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (40)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill is presented as project-organization scaffolding, but it also includes OpenCode SQLite project-database inspection/modification, deletion of project records, optional remote hub cleanup over SSH, and service-remediation steps. This hidden expansion of authority is dangerous because an agent or user may invoke the skill expecting local organization only, while it can alter local metadata and remote synchronized state with potentially irreversible side effects.

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 109)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 110)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 292)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 318)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 360)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 429)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 436)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 441)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 535)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 553)May include surrounding context.

md
son` / `.gitignore` / `.gitattributes`、目录 `.git/` 与上述目录(含 `buffer/`),其余一律视为散落物(`audit_project.py` 会报)。**例外**:项目若确有合法根级扩展,可在 `.bigproject.json` 的 `root_extension

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill describes and instructs use of file I/O, environment-variable resolution, and shell-driven scripts, but it does not declare an explicit tool scope such as permissions or allowed-tools. That increases the chance an agent will invoke broad local capabilities implicitly, including destructive filesystem actions, without a machine-checkable boundary.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The activation boundary mixes broad descriptive criteria with loose trigger phrases and only partially distinguishes itself from adjacent workflows like temporary workspaces. Ambiguous activation is risky here because the skill includes mutating operations—moving files, trashing items, initializing git, and potentially invoking DB-repair guidance—so accidental invocation can have real side effects.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad and overlap with common terms like project management, organization, and directory cleanup. That makes over-activation likely, causing the agent to apply a high-authority skill in contexts where the user did not intend filesystem restructuring, git changes, or soft-deletion workflows.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documented oc_project_link.py capability goes beyond organizing project files and performs direct cleanup of project records, including optional synchronized hub deletion via SSH. Even if intended as remediation, bundling unrelated state-modification functions into a general organization skill creates confused-deputy risk and increases the chance of accidental metadata loss.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains natural-language instructions and output descriptions entirely in Chinese, and later user-facing CLI/help/error strings are also Chinese-only. The file does not indicate that the skill is region-specific or provide any user opt-in or language selection, which can violate a language/locale policy requiring user choice.

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/audit_project.py (reported line 177)May include surrounding context.

python
rel = child.relative_to(root).as_posix()
                ignored = False
                try:
                    r = subprocess.run(["git", "-C", str(root), "check-ignore", "-q", rel],
                                       capture_output=True)
                    ignored = (r.returncode == 0)
                except Exception:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring and all user-facing help/error text in this file are written in Chinese, which imposes a specific language/locale on users. The file does not indicate any opt-in, fallback, or user-selectable language behavior, so this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code file contains natural-language documentation entirely in Chinese and labels the utilities as '公共工具', which indicates a fixed language/locale expectation for users and maintainers. Under the stated policy, forcing a specific language without user opt-in or documented regional justification is a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module docstring and all user-facing help text are written only in Chinese, effectively forcing a specific language/locale for users of the skill. The policy allows locale constraints only when they are explicitly justified or when the user is offered a language choice, neither of which is present here.

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/git_setup.py (reported line 46)May include surrounding context.

python
def _git(root, *args, timeout=120):
    return subprocess.run(["git", *args], cwd=str(root), capture_output=True,
                          text=True, encoding="utf-8", errors="replace", timeout=timeout)

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/git_setup.py (reported line 52)May include surrounding context.

python
def git_available():
    try:
        r = subprocess.run(["git", "--version"], capture_output=True, text=True, timeout=20)
        return r.returncode == 0, (r.stdout or r.stderr or "").strip()
    except Exception as e:  # noqa: BLE001
        return False, str(e)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The natural-language documentation and user-facing descriptions in this file are entirely in Chinese, which imposes a specific language/locale on users without offering a choice or documenting that the skill is region-specific. The policy allows locale constraints only when clearly justified or opt-in is provided, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file’s user-facing natural language is entirely Chinese, including the top-level description, usage context, and emitted/help text, with no indication that another language is supported or that the language is region-specific by design. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.