codepulse-ext
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest the entire contents of a codebase for security analysis, creating a surface for indirect prompt injection attacks. An attacker could place malicious instructions within code comments or files that influence the agent's reasoning or corrupt the generated HTML report.\n
- Ingestion points: The skill instructions in
SKILL.mdexplicitly direct the agent to "Use the entire codebase as the context for this skill."\n - Boundary markers: There are no requirements or delimiters defined in
SKILL.mdto help the agent distinguish between its instructions and the data being analyzed (the codebase).\n - Capability inventory: The skill is capable of writing HTML files to the local file system (
codepulse-ext/reports/).\n - Sanitization: The skill lacks instructions for sanitizing or escaping content extracted from the codebase before it is interpolated into the
report-template.htmlfor final output.
Audit Metadata