skills/jgabor/agentera/dokumentera/Gen Agent Trust Hub

dokumentera

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process untrusted data from the local codebase (source code, existing documentation files, and git history).
  • Ingestion points: Where untrusted data enters agent context: SKILL.md (Step 1: Explore) and Update-and-verify mode (Step 1: Discover) read various files including source code, manifests, and existing documentation.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or system-level instructions to ignore embedded commands within the files being read.
  • Capability inventory: The skill is capable of reading project files, writing to the file system (standard documentation artifacts), and executing shell commands (git log, git mv).
  • Sanitization: Absent. There is no explicit requirement to sanitize or escape data read from the project files before re-incorporating it into documentation drafts.
  • [COMMAND_EXECUTION]: The skill instructions include the execution of standard version control commands (git log, git mv) to inspect project history and perform documentation restructuring. These operations are within the expected scope of a documentation management tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 07:29 AM