crest-narrative
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is instructed to aggregate data from external sources that may contain untrusted content.
- Ingestion points: Step 1 in SKILL.md directs the agent to collect data from sources named 'Lumen' (traction), 'Echo' (user insights), 'crest-compete' (competitive position), and 'crest-okr' (objectives), some of which likely contain raw user input or external market data.
- Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to prevent the agent from being influenced by instructions embedded within the ingested data.
- Capability inventory: The skill's environment allows access to high-privilege tools such as 'Bash', 'Write', 'Edit', and 'WebFetch', which could be leveraged if an indirect injection attack is successful.
- Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from these sources before it is incorporated into the strategy memo generation process.
Audit Metadata