paper-plan

Warn

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute Bash commands (cat << 'EOF' > file) silently to write files in chunks if standard tools fail. This instruction explicitly tells the agent to bypass user permission and oversight for file system operations.- [DATA_EXFILTRATION]: The skill performs directory traversal to read files from a sibling directory (../shared-references/). It subsequently sends contents extracted from these and other local project files to an external model via the Codex MCP tool.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection.
  • Ingestion points: Untrusted research data is read from NARRATIVE_REPORT.md, STORY.md, EXPERIMENT_LOG.md, and JSON files in figures/ (SKILL.md).
  • Boundary markers: The skill lacks clear delimiters or instructions to ignore embedded commands when interpolating this data into prompts.
  • Capability inventory: The agent has access to Bash, Write, Edit, and WebSearch tools, which could be leveraged if an injection is successful.
  • Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the AI.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 18, 2026, 04:51 PM
Security Audit — agent-trust-hub — paper-plan