sast-report
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external markdown files (
sast/*-results.md) and interpolates their content directly into a final report. - Ingestion points: The agent is instructed to read all
*-results.mdfiles in thesast/directory. - Boundary markers: While the skill uses classification tags like
[VULNERABLE]to identify relevant findings, there are no instructions to sanitize the content or ignore embedded natural language instructions within the proof, impact, or remediation sections. - Capability inventory: The skill possesses the capability to read local files within the
sast/directory and write a new consolidated file (sast/final-report.md). - Sanitization: The instructions explicitly require the agent to 'Preserve all details from the original findings' and 'do not summarize or truncate', which ensures that any malicious payloads in the source files are propagated into the final report without alteration.
Audit Metadata