project-wiki

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core workflow involves reading and analyzing external project files, source code, and existing documentation to generate new content.\n
  • Ingestion points: The agent is instructed to scan project structures and parse file contents as part of its 'Extraction' and 'Information Review' steps as defined in SKILL.md and references/knowledge/extraction.md.\n
  • Boundary markers: No specific delimiters or boundary instructions are provided to isolate untrusted project content from the agent's core instructions.\n
  • Capability inventory: The agent is empowered to generate and write project-level documentation, meaning malicious input could influence the content of generated output files.\n
  • Sanitization: No documented procedures for sanitizing or validating ingested project content are implemented in the guides or templates.\n- [NO_CODE]: The analyzed skill consists exclusively of 34 Markdown documentation and template files, with no executable scripts, binaries, or automated code components found in the audited content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:49 PM