document-project

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection through the analysis of project files.
  • Ingestion points: The skill performs extensive reading of local project data, including manifests (package.json, pyproject.toml, Cargo.toml), existing documentation files (.md, .rst, .adoc), and source code directories (SKILL.md).
  • Boundary markers: Absent. The skill lacks instructions or delimiters to prevent the agent from following instructions embedded within the untrusted project files it audits.
  • Capability inventory: The skill utilizes Bash, Write, and Edit tools (SKILL.md), enabling it to execute commands and modify the filesystem based on the analysis of ingested data.
  • Sanitization: Absent. There is no evidence of filtering or validation for content extracted from the project files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 03:04 PM
Security Audit — agent-trust-hub — document-project