fec-code-review

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it ingests untrusted data from project files and has the capability to execute commands. 1. Ingestion points: According to SKILL.md, the agent reads project facts, package scripts, frameworks, directory conventions, diffs, and tests. 2. Boundary markers: The instructions lack specific delimiters or warnings to the agent to ignore instructions embedded in the code it reads. 3. Capability inventory: The agent is authorized to run project-wide linting and type-checking commands and to write report files to the reports/ directory. 4. Sanitization: No process for sanitizing or validating the content of the ingested files is described.
  • [COMMAND_EXECUTION]: The skill enables the agent to execute shell-based commands for project verification, specifically mentioned as running lint and type-checking tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 01:10 AM