fedir-claude-compression
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary text input provided as an agent or skill definition, which creates a surface for indirect prompt injection attacks.
- Ingestion points: External content is ingested through the
<AGENT_OR_SKILL_DEFINITION>placeholder inSKILL.md. - Boundary markers: The skill does not provide the LLM with explicit delimiters or instructions to ignore instructions embedded within the data being processed.
- Capability inventory: The skill lacks any dangerous capabilities such as file system access, network operations, or subprocess execution, which significantly limits the potential impact of a successful injection.
- Sanitization: No sanitization or validation of the input content is performed to ensure it only contains passive data rather than actionable instructions.
Audit Metadata