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.mdandCONTEXT-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.mdandreferences/asd-ste100-profile.mdinstruct the agent to read and use data fromCONTEXT.mdandCONTEXT-MAP.mdto 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