doc-iplan-audit

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core function of ingesting and analyzing untrusted user documentation.
  • Ingestion points: Documentation content is ingested from files matching docs/08_IPLAN/IPLAN-NN_*.yaml in SKILL.md.
  • Boundary markers: Absent. The skill does not define clear delimiters or specific instructions to ignore embedded commands within the artifact content passed to sub-agents.
  • Capability inventory: The skill executes shell commands (mkdir, date, cat) and manages multiple sub-agent tasks in SKILL.md.
  • Sanitization: Partial. The skill implements a citation requirement where findings must reference specific playbook checks, and the synthesizer agent filters out findings that lack proper citations.
  • [COMMAND_EXECUTION]: The skill uses shell commands for project management and execution tracking.
  • Specifically, it uses mkdir -p, date +%s, cat, and echo to manage review directories and calculate elapsed time for circuit-breaking (timeout enforcement) in the .aidoc/ directory.
  • These commands are standard for the skill's operational logic and do not appear to incorporate unsanitized user input into the command strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:55 PM
Security Audit — agent-trust-hub — doc-iplan-audit