idea-autopsy
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of a local project file, which creates a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read the contents of
REJECTION.mdat the start of the workflow (Step 1). - Boundary markers: There are no specified delimiters or instructions to isolate the data in
REJECTION.md, allowing the agent to potentially follow instructions embedded within the file. - Capability inventory: The skill identifies and modifies the project state by reading and appending to the
REJECTION.mdfile. - Sanitization: The skill does not describe any methods for sanitizing or validating the content retrieved from the file before it is interpreted by the agent.
- [NO_CODE]: This skill consists entirely of natural language instructions and does not include any scripts or executable code.
Audit Metadata