Back to skill

Security audit

Analyse pièce comptable

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only helper for analyzing one accounting document locally, with no evidence of hidden network access, persistence, or destructive behavior.

Install only if you expect the agent to read sensitive accounting documents locally. The skill is narrowly read-only, but users should be aware it will process invoice, bank-statement, and expense-report contents and depends on local PDF/OCR tools, primarily tuned for French documents.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

La description d’activation est trop large car elle autorise un déclenchement implicite « quand une pièce jointe arrive », sans signal clair de l’utilisateur ni cadrage explicite du contexte. Cela peut amener l’agent à ouvrir et analyser automatiquement des documents sensibles ou non pertinents, augmentant le risque d’accès excessif aux données et d’actions hors intention de l’utilisateur.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

La documentation, les messages de sortie et les libellés de contrôle sont rédigés uniquement en français, ce qui constitue une contrainte de langue visible pour l'utilisateur. Le fichier n'offre aucun mécanisme d'opt-in, de sélection de langue, ni justification claire d'un périmètre strictement francophone ou régional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This code file contains natural-language guidance and implementation choices such as tesseract -l fra and French-only labels that effectively impose a specific language/locale. Under the policy rule, forcing a language without user opt-in or explicit justified locale scoping is a violation.

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/extract.py (reported line 152)May include surrounding context.

python
with tempfile.TemporaryDirectory() as td:
        prefix = os.path.join(td, "p")
        try:
            subprocess.run(["pdftoppm", "-png", "-r", str(dpi), "-l", str(max_pages),
                            str(path), prefix], capture_output=True, timeout=180)
        except Exception:
            return ""

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/extract.py (reported line 158)May include surrounding context.

python
return ""
        for png in sorted(f for f in os.listdir(td) if f.endswith(".png")):
            try:
                r = subprocess.run(
                    ["tesseract", os.path.join(td, png), "stdout", "-l", "fra", "--psm", "6", "tsv"],
                    capture_output=True, text=True, errors="ignore", timeout=120)
                out.append(_tsv_to_layout(r.stdout))

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/extract.py (reported line 180)May include surrounding context.

python
best = ""
    for args in (["-layout"], ["-raw"], []):
        try:
            r = subprocess.run(["pdftotext", *args, str(path), "-"],
                               capture_output=True, text=True, errors="ignore", timeout=30)
        except Exception:
            continue

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/extract.py (reported line 1322)May include surrounding context.

python
os.makedirs(out_dir, exist_ok=True)
    prefix = os.path.join(out_dir, "page")
    try:
        subprocess.run(["pdftoppm", "-png", "-r", str(dpi), "-l", str(max_pages),
                        str(pdf_path), prefix], capture_output=True, timeout=120)
    except Exception:
        return []