01-traceability-matrix
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process several user-provided external files (SRS_Draft.md, vision.md, HLD.md, LLD.md, user_stories.md) as part of its core logic. These files are processed to extract identifiers and requirements without explicit instructions to the AI agent to ignore any embedded directives within the content. This could allow an attacker to influence agent behavior by placing malicious instructions inside the documentation being analyzed.
- Ingestion points: Defined in both
SKILL.md(Core Instructions 1-4) andlogic.prompt(Steps 1-3), involving the reading of multiple markdown files from the project context. - Boundary markers: Absent. The instructions do not specify delimiters or provide warnings to the agent to treat the ingested file content strictly as data.
- Capability inventory: The skill possesses the capability to read project files and write to the file system (specifically
Traceability_Matrix.mdandmanifest.md). - Sanitization: None provided. The skill extracts text segments and identifiers directly from the sources into the output report.
Audit Metadata