skills/posit-dev/skills/alt-text/Gen Agent Trust Hub

alt-text

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs standard shell commands such as ls and grep to detect project types (pkgdown or Quarto) and to audit files for missing alt text. These commands are executed locally within the project scope and do not involve any high-risk operations or privilege escalation.\n- [INDIRECT_PROMPT_INJECTION]: The skill analyzes source code and prose from project files to draft descriptive text, which constitutes an ingestion surface for untrusted data.\n
  • Ingestion points: Content is read from vignettes/, README.md, and R source files (R/*.R).\n
  • Boundary markers: The instructions do not define specific delimiters or directives to isolate project content from the agent's instructions.\n
  • Capability inventory: The skill uses local file search and auditing via ls and grep, and involves context for writing/updating files.\n
  • Sanitization: There is no explicit sanitization or filtering of the content extracted from the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:38 PM
Security Audit — agent-trust-hub — alt-text