skills/bbenefield89/skills/asd-ste100/Gen Agent Trust Hub

asd-ste100

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the project workspace (specifically CONTEXT.md and CONTEXT-MAP.md) to extract terminology. This creates a surface where an attacker could place malicious instructions inside those files to influence the AI's output.
  • Ingestion points: SKILL.md and references/asd-ste100-profile.md instruct the agent to read and use data from CONTEXT.md and CONTEXT-MAP.md to resolve terminology.
  • Boundary markers: None. The skill does not provide delimiters or instructions to ignore potential commands within the external terminology files.
  • Capability inventory: No tools are explicitly requested in the skill's frontmatter, which limits the potential impact of an injection to the text generation phase.
  • Sanitization: The skill contains no instructions or logic to sanitize or validate the content of the external terminology files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:17 PM
Security Audit — agent-trust-hub — asd-ste100