skills/nathanab/corpus-skill/corpus/Gen Agent Trust Hub

corpus

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill manages a workflow for processing untrusted external data, which creates an indirect prompt injection vulnerability surface.\n
  • Ingestion points: The skill ingests external files and directories into the corpus/ directory as part of the references/ingest.md workflow.\n
  • Boundary markers: Both references/consult.md and references/ingest.md include explicit instructions for the agent to treat source content as "untrusted data" and to specifically avoid following instructions found within evidence.\n
  • Capability inventory: The skill is capable of reading local files, writing to the corpus/ directory, modifying the repository's .gitignore file, and updating or creating the agent instruction file AGENTS.md.\n
  • Sanitization: Ingestion workflows in references/ingest.md mandate faithful extraction of text without added interpretation or summaries, which helps mitigate the risk of the agent being misled by malicious content during the ingestion process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 08:03 PM
Security Audit — agent-trust-hub — corpus